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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soda
    -0.07
    ogl
    -0.06
    _SAN
    -0.06
     Castle
    -0.06
     upwards
    -0.06
     beers
    -0.06
     breakdown
    -0.06
     vegetables
    -0.06
    iac
    -0.06
     alcohol
    -0.06
    POSITIVE LOGITS
    ')],↵
    0.07
     ΑΓ
    0.07
    SmartyHeaderCode
    0.07
    =date
    0.07
    _vue
    0.07
    csrf
    0.06
    trys
    0.06
    (['
    0.06
     filmm
    0.06
    132
    0.06
    Act Density 0.000%

    No Known Activations