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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Afterwards
    -0.07
    .twitter
    -0.07
     اینترنتی
    -0.06
    .Car
    -0.06
     kot
    -0.06
    .Download
    -0.06
     kitab
    -0.06
    _ts
    -0.06
     headset
    -0.06
     Hra
    -0.06
    POSITIVE LOGITS
    安全
    0.07
    역
    0.07
    リング
    0.06
    難
    0.06
    encing
    0.06
    ecedor
    0.06
    政治
    0.06
    <File
    0.06
     outcome
    0.06
    IL
    0.06
    Act Density 0.003%

    No Known Activations