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

    Neuronpedia

    INDEX
    Explanations

    sensitivity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mime
    -0.07
    ाग
    -0.06
    CT
    -0.06
    ког
    -0.06
    _test
    -0.06
     collapsing
    -0.06
     recruit
    -0.06
     Wash
    -0.06
     små
    -0.06
    Sharper
    -0.06
    POSITIVE LOGITS
     wn
    0.07
     Yunan
    0.07
    klär
    0.07
    OutOfRangeException
    0.07
     habil
    0.07
     erle
    0.06
     overl
    0.06
    ائی
    0.06
    .shiro
    0.06
     combineReducers
    0.06
    Act Density 0.005%

    No Known Activations