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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Abdul
    -0.07
    joint
    -0.07
     kot
    -0.06
     菲律宾申博
    -0.06
    ає
    -0.06
    言う
    -0.06
    truck
    -0.06
    �
    -0.06
    説明
    -0.06
     установки
    -0.06
    POSITIVE LOGITS
     priv
    0.07
    _scal
    0.06
    /*================================================================
    0.06
     artifacts
    0.06
    suspend
    0.06
     palette
    0.06
    .Resize
    0.06
    _message
    0.06
    onavir
    0.06
    _twitter
    0.06
    Act Density 0.038%

    No Known Activations