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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (�
    -0.07
    _width
    -0.07
     april
    -0.07
    _tick
    -0.06
    SETS
    -0.06
    .velocity
    -0.06
    .recv
    -0.06
    _uid
    -0.06
    protocols
    -0.06
     Statistical
    -0.06
    POSITIVE LOGITS
     зрения
    0.07
    olf
    0.06
     있었다
    0.06
    ，用
    0.06
    inging
    0.06
     son
    0.06
    Are
    0.06
     Seller
    0.06
    abl
    0.06
     observing
    0.06
    Act Density 0.000%

    No Known Activations