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

    Neuronpedia

    INDEX
    Explanations

    math symbols and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erval
    -0.08
    анк
    -0.08
     pato
    -0.07
    pecified
    -0.07
    VER
    -0.07
     timid
    -0.07
    quisition
    -0.07
     sluggish
    -0.07
    IAN
    -0.07
    IVAL
    -0.07
    POSITIVE LOGITS
     normalization
    0.08
     còn
    0.08
     оста
    0.08
    Normalization
    0.07
     overpower
    0.07
     existe
    0.07
     normalize
    0.07
     kosmet
    0.07
     Σε
    0.07
     आगे
    0.07
    Act Density 0.016%

    No Known Activations