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

    Neuronpedia

    INDEX
    Explanations

    vote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tongue
    -0.07
    neath
    -0.07
     butter
    -0.06
     filmpjes
    -0.06
    ходим
    -0.06
    guna
    -0.06
     governors
    -0.06
     Liqu
    -0.06
    ']='
    -0.06
     Ch
    -0.06
    POSITIVE LOGITS
    \Desktop
    0.06
    EmailAddress
    0.06
     bầu
    0.06
    !↵↵↵↵
    0.06
     jm
    0.06
    -national
    0.06
     Βροχή
    0.06
    �
    0.06
    HS
    0.06
     getHeight
    0.06
    Act Density 0.004%

    No Known Activations