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

    Neuronpedia

    INDEX
    Explanations

    layer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Benn
    -0.07
     Quinn
    -0.07
     Cincinnati
    -0.07
     complained
    -0.07
     Turnbull
    -0.06
    に出
    -0.06
     Bennett
    -0.06
     buf
    -0.06
     should
    -0.06
     enthusiastic
    -0.06
    POSITIVE LOGITS
     layer
    0.16
     Layer
    0.15
     layers
    0.14
    Layer
    0.14
    layer
    0.13
    layers
    0.12
    -layer
    0.12
    ayer
    0.12
     Layers
    0.11
     layered
    0.11
    Act Density 0.019%

    No Known Activations