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

    Neuronpedia

    INDEX
    Explanations

    inter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    veyor
    -0.07
    Snackbar
    -0.06
    цями
    -0.06
    цами
    -0.06
    lander
    -0.06
    _metadata
    -0.06
    مي
    -0.06
    omething
    -0.06
    _series
    -0.06
     поля
    -0.06
    POSITIVE LOGITS
     ripped
    0.07
     απ
    0.07
     حف
    0.07
    joint
    0.06
     الف
    0.06
     grou
    0.06
    oved
    0.06
    Enums
    0.06
    	Il
    0.06
     FTP
    0.06
    Act Density 0.001%

    No Known Activations