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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    442
    -0.06
    /op
    -0.06
     hvě
    -0.06
    066
    -0.06
    ichel
    -0.06
     Jord
    -0.06
    ottle
    -0.06
     Erick
    -0.06
    隐
    -0.06
    plants
    -0.05
    POSITIVE LOGITS
     neby
    0.07
    SourceType
    0.07
    _Type
    0.07
     Determines
    0.06
    илось
    0.06
     Getter
    0.06
    .Read
    0.06
    센
    0.06
     Dota
    0.06
     سور
    0.06
    Act Density 0.011%

    No Known Activations