Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms related to regulation and control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after initial words/phrases

    np_acts-logits-general · gemini-2.0-flash

    except forbut inaccurategave ittwo lettersdecreased glycineresult there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leſs
    -0.69
     itſelf
    -0.67
     faſt
    -0.65
     hänen
    -0.64
     raiſ
    -0.64
    ChildScrollView
    -0.63
     ſen
    -0.61
     ſtre
    -0.61
     ſever
    -0.61
     houſe
    -0.61
    POSITIVE LOGITS
     lavander
    0.59
     wood
    0.57
     Bra
    0.57
     jScrollPane
    0.56
     Micro
    0.55
    FieldBuilder
    0.54
    ppé
    0.54
     iPad
    0.54
     Water
    0.54
    opress
    0.53
    Act Density 3.242%

    No Known Activations