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

    Neuronpedia

    INDEX
    Explanations

    arch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -control
    -0.07
    лага
    -0.07
    -kind
    -0.07
    ına
    -0.06
    strong
    -0.06
     Ist
    -0.06
    ingredients
    -0.06
     KG
    -0.06
    قية
    -0.06
     because
    -0.06
    POSITIVE LOGITS
    (ray
    0.07
     Responses
    0.07
    DEBUG
    0.07
    OURCE
    0.07
    &↵
    0.07
     Crimes
    0.06
     hoop
    0.06
    ेण
    0.06
    ’acc
    0.06
     incorporating
    0.06
    Act Density 0.013%

    No Known Activations