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

    Neuronpedia

    INDEX
    Explanations

    motel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pecies
    -0.08
     expenditure
    -0.08
    除尘
    -0.08
    之情
    -0.07
    见
    -0.07
     tobacco
    -0.07
    .Batch
    -0.07
     organis
    -0.07
    .launch
    -0.07
     solvent
    -0.07
    POSITIVE LOGITS
    섞
    0.09
     Mons
    0.07
     crippling
    0.07
     Altın
    0.07
    fef
    0.07
     explorer
    0.07
    думал
    0.07
    Schedulers
    0.06
    翙
    0.06
    助手
    0.06
    Act Density 0.016%

    No Known Activations