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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ْد
    -0.07
     ヴ
    -0.06
    вание
    -0.06
     debug
    -0.06
    ?',
    -0.06
     conservatism
    -0.06
    Div
    -0.06
     carbohydr
    -0.06
    attachments
    -0.06
     rau
    -0.06
    POSITIVE LOGITS
    OSC
    0.07
    (KP
    0.07
    .wx
    0.06
     سلس
    0.06
    (LP
    0.06
    _JUMP
    0.06
    (payment
    0.06
    เลข
    0.06
    فت
    0.06
    \Auth
    0.06
    Act Density 0.152%

    No Known Activations