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

    Neuronpedia

    INDEX
    Explanations

    archives/collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %)$
    -0.72
    archives
    -0.63
    glio
    -0.59
    |
    -0.54
    ']))
    -0.54
    ()))
    -0.54
    ])
    -0.54
    __":
    -0.53
     otomatig
    -0.52
    hex
    -0.51
    POSITIVE LOGITS
     hObject
    0.74
     noDo
    0.66
     незавершена
    0.60
    hips
    0.60
    manship
    0.58
    elemField
    0.58
    bows
    0.58
     Sopho
    0.57
    BeginInit
    0.56
    Воспита
    0.55
    Act Density 0.807%

    No Known Activations