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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lado
    -0.07
    �
    -0.07
    side
    -0.07
     democratic
    -0.07
     glow
    -0.06
    收
    -0.06
    Miami
    -0.06
     csak
    -0.06
    view
    -0.06
    .ค
    -0.06
    POSITIVE LOGITS
    Wenn
    0.07
    ATORS
    0.06
    agers
    0.06
    erti
    0.06
    _sal
    0.06
     dame
    0.06
     keyboardType
    0.06
    �
    0.06
     PyErr
    0.06
    .px
    0.06
    Act Density 0.073%

    No Known Activations