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

    Neuronpedia

    INDEX
    Explanations

    faith

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kręc
    -0.08
    utr
    -0.07
    🤾
    -0.07
    礞
    -0.07
     обслужива
    -0.07
    _KP
    -0.07
    �
    -0.07
     carbohydr
    -0.07
    .visitMethod
    -0.07
    .if
    -0.07
    POSITIVE LOGITS
    бар
    0.07
    post
    0.07
     vị
    0.07
    aret
    0.07
     line
    0.07
    았
    0.07
    runtime
    0.06
    ミ
    0.06
     shy
    0.06
    _removed
    0.06
    Act Density 0.003%

    No Known Activations