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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Native
    -0.06
    .Models
    -0.06
     CC
    -0.06
     villages
    -0.06
     pelvic
    -0.06
     Huckabee
    -0.06
    Outputs
    -0.05
    _district
    -0.05
    }];↵
    -0.05
    eği
    -0.05
    POSITIVE LOGITS
     Term
    0.08
     dlouho
    0.07
    UID
    0.07
     WARN
    0.07
    expert
    0.07
     Hij
    0.07
    없
    0.07
    .д
    0.07
     expo
    0.07
     esp
    0.06
    Act Density 0.012%

    No Known Activations