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

    Neuronpedia

    INDEX
    Explanations

    frequency amplitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forgiving
    -0.07
    _black
    -0.06
     generic
    -0.06
     Barry
    -0.06
     Fol
    -0.06
     Pants
    -0.06
     landing
    -0.06
    효
    -0.06
     Armstrong
    -0.06
     RJ
    -0.06
    POSITIVE LOGITS
     yapım
    0.07
     århus
    0.07
    .Drawable
    0.06
    ASE
    0.06
    (changes
    0.06
    िच
    0.06
    Due
    0.06
    更加
    0.06
    简
    0.06
    สาย
    0.06
    Act Density 0.072%

    No Known Activations