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

    Neuronpedia

    INDEX
    Explanations

    official documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timber
    -0.06
     Stories
    -0.06
    lerimiz
    -0.06
     sounds
    -0.06
     magazine
    -0.06
    ائق
    -0.06
     XF
    -0.06
     vb
    -0.06
    یس
    -0.06
    刺
    -0.06
    POSITIVE LOGITS
     differentiate
    0.07
    (Category
    0.06
     Communications
    0.06
     encour
    0.06
    (Control
    0.06
    _SEGMENT
    0.06
     prázd
    0.06
     estão
    0.06
     getMax
    0.06
     komplex
    0.06
    Act Density 0.001%

    No Known Activations