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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes and the sharing of ideas

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

    Followed by "some"

    np_acts-logits-general · gemini-2.0-flash

    some [abstract noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     totalité
    -0.62
     autant
    -0.62
     entire
    -0.62
     entirety
    -0.59
     segala
    -0.59
     wszel
    -0.59
     détru
    -0.57
    EXACT
    -0.57
     complètes
    -0.56
     exact
    -0.56
    POSITIVE LOGITS
     nakalista
    0.93
     some
    0.88
    some
    0.84
     algunas
    0.81
    Some
    0.79
     Algunos
    0.79
    Algunos
    0.78
    SOME
    0.78
    Algunas
    0.75
     Algunas
    0.75
    Act Density 0.254%

    No Known Activations