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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cast
    -0.08
    .resize
    -0.08
     Identified
    -0.08
    veget
    -0.07
    boBox
    -0.07
    Balance
    -0.07
     conducts
    -0.06
     vibrant
    -0.06
     adul
    -0.06
    .firebaseio
    -0.06
    POSITIVE LOGITS
     Marcos
    0.07
    的には
    0.07
    ред
    0.07
    קהל
    0.07
    kur
    0.07
     Erdogan
    0.06
     trường
    0.06
    ود
    0.06
     Frage
    0.06
     Как
    0.06
    Act Density 0.002%

    No Known Activations