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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mh
    -0.07
     CSC
    -0.07
    IRROR
    -0.07
    !='
    -0.07
    ่าท
    -0.07
     contradict
    -0.06
    _RS
    -0.06
     gains
    -0.06
    ACTION
    -0.06
     Jak
    -0.06
    POSITIVE LOGITS
    ические
    0.07
    田
    0.06
    Cancelable
    0.06
    ibile
    0.06
    ).(
    0.06
    helm
    0.06
     continually
    0.06
    ต
    0.06
    StyleSheet
    0.06
    äre
    0.06
    Act Density 0.110%

    No Known Activations