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

    Neuronpedia

    INDEX
    Explanations

    Medical symptoms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Turk
    -0.09
     metaphor
    -0.07
     memo
    -0.07
     cont
    -0.07
     commentary
    -0.07
    TouchableOpacity
    -0.06
     ctrl
    -0.06
     CODE
    -0.06
    cls
    -0.06
    นใจ
    -0.06
    POSITIVE LOGITS
    坂
    0.07
     Colomb
    0.07
    lararası
    0.06
     Returned
    0.06
    ])↵↵↵
    0.06
    ','.
    0.06
    elfast
    0.06
    .Reporting
    0.06
    haar
    0.06
    經
    0.06
    Act Density 0.063%

    No Known Activations