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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beta
    -0.07
    ATAL
    -0.07
    打
    -0.07
     대
    -0.07
     PICK
    -0.07
    atched
    -0.07
    *B
    -0.07
     batter
    -0.07
     Rat
    -0.06
    -beta
    -0.06
    POSITIVE LOGITS
    6
    0.13
    46
    0.09
    Moon
    0.08
     Laurie
    0.08
    语
    0.08
     Mitgli
    0.08
    ห
    0.08
    ासन
    0.08
    ่วม
    0.08
    Fran
    0.08
    Act Density 0.295%

    No Known Activations