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

    Neuronpedia

    INDEX
    Explanations

    minimum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prenom
    -0.08
     Declarations
    -0.07
     Expense
    -0.07
     ents
    -0.07
    ڽ
    -0.07
     bones
    -0.07
    І
    -0.07
    quisition
    -0.07
    ༚
    -0.06
    排
    -0.06
    POSITIVE LOGITS
    -binary
    0.07
     brib
    0.07
    .up
    0.07
    -shadow
    0.07
     Alexa
    0.07
     wiki
    0.07
    챠
    0.06
    .dataset
    0.06
     técnico
    0.06
     Facebook
    0.06
    Act Density 0.004%

    No Known Activations