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

    Neuronpedia

    INDEX
    Explanations

    references to personal connections and shared experiences

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

    Text after commas

    np_acts-logits-general · gemini-2.0-flash

    states and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    theless
    -0.64
    AnchorStyles
    -0.64
    клопе
    -0.63
    anmoins
    -0.63
    NUMX
    -0.61
    VersionUID
    -0.61
    lankton
    -0.59
    Additionally
    -0.56
    Außerdem
    -0.56
     >=",
    -0.55
    POSITIVE LOGITS
     belki
    0.52
    ctrica
    0.50
     like
    0.49
     lignin
    0.49
    甚至是
    0.47
    oa̍t
    0.47
    ,
    0.47
     even
    0.46
     hatta
    0.46
     nélkül
    0.46
    Act Density 0.307%

    No Known Activations