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

    Neuronpedia

    INDEX
    Explanations

    comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exclus
    -0.08
     statistically
    -0.08
     clandest
    -0.08
     probabil
    -0.07
     amplitude
    -0.07
     qu
    -0.07
     grapes
    -0.07
    nev
    -0.07
     بالنسبة
    -0.07
    host
    -0.07
    POSITIVE LOGITS
     пояс
    0.08
     POWER
    0.08
     Everywhere
    0.08
    ","#
    0.08
     된
    0.08
     statements
    0.08
     yle
    0.08
     щоб
    0.08
     Statements
    0.07
     어
    0.07
    Act Density 0.004%

    No Known Activations