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

    Neuronpedia

    INDEX
    Explanations

    IT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    <dim
    -0.07
    brief
    -0.07
    >Z
    -0.07
    _z
    -0.06
    ha
    -0.06
    hard
    -0.06
    .available
    -0.06
     ParameterDirection
    -0.06
     kald
    -0.06
    POSITIVE LOGITS
     enqu
    0.08
    .contact
    0.08
    uttle
    0.07
     shutter
    0.07
    .Inst
    0.06
    zelf
    0.06
    优
    0.06
    0.06
    Utility
    0.06
     Cecil
    0.06
    Act Density 0.000%

    No Known Activations