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

    Neuronpedia

    INDEX
    Explanations

    up down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warehouses
    -0.06
    _CAPACITY
    -0.06
     athlete
    -0.06
     TZ
    -0.06
    -era
    -0.06
     withheld
    -0.06
    73
    -0.06
    672
    -0.06
    70
    -0.06
     genomes
    -0.06
    POSITIVE LOGITS
     deutsch
    0.07
     طبی
    0.07
     кня
    0.07
     (^
    0.06
     SAY
    0.06
     Bloss
    0.06
    .Mod
    0.06
    대비
    0.06
    ポ
    0.06
     inser
    0.06
    Act Density 0.047%

    No Known Activations