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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
    _py
    -0.06
    ce
    -0.06
    Spark
    -0.06
    Reducer
    -0.06
     ด
    -0.06
     forks
    -0.06
     Ở
    -0.06
    dız
    -0.06
     infl
    -0.06
    POSITIVE LOGITS
     sehen
    0.06
    -zA
    0.06
    ACHINE
    0.06
     individuals
    0.06
    anness
    0.06
     Exclude
    0.06
    edish
    0.06
     erotico
    0.06
    殺
    0.06
    hosts
    0.06
    Act Density 0.145%

    No Known Activations