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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/Codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kayıt
    -0.07
    (D
    -0.06
     thần
    -0.06
    (queue
    -0.06
    %;">
    -0.06
    (f
    -0.06
    یف
    -0.06
     fonction
    -0.06
     quitting
    -0.06
     muted
    -0.06
    POSITIVE LOGITS
    0.06
    棒
    0.06
     disput
    0.06
     ux
    0.06
    _alert
    0.06
    ifying
    0.06
     thuộc
    0.06
    annual
    0.06
    uyển
    0.06
    食
    0.06
    Act Density 0.001%

    No Known Activations