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

    Neuronpedia

    INDEX
    Explanations

    jump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reversed
    -0.08
    ード
    -0.07
     waived
    -0.07
     XYZ
    -0.07
     operador
    -0.07
     opposite
    -0.07
    菲律宾
    -0.07
     director
    -0.07
    绿
    -0.07
     Jamaican
    -0.07
    POSITIVE LOGITS
     increments
    0.17
    increment
    0.16
    increments
    0.15
    _INCREMENT
    0.15
    _increment
    0.14
    Increment
    0.14
    .increment
    0.14
     incremental
    0.14
     increment
    0.14
     monoton
    0.14
    Act Density 0.023%

    No Known Activations