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

    Neuronpedia

    INDEX
    Explanations

    recipe servings/quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggress
    -0.07
     Kar
    -0.06
    Jeremy
    -0.06
    ्थ
    -0.06
     erratic
    -0.06
     boosting
    -0.06
    emed
    -0.06
    adian
    -0.06
     vulnerabilities
    -0.06
    blogs
    -0.06
    POSITIVE LOGITS
    Chuck
    0.08
    ψη
    0.07
     indiscrim
    0.07
    lets
    0.07
    (ARG
    0.06
    .Ext
    0.06
    ческая
    0.06
    _PRODUCT
    0.06
    _range
    0.06
    _requirements
    0.06
    Act Density 0.010%

    No Known Activations