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

    Neuronpedia

    INDEX
    Explanations

    discounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ану
    -0.07
     verso
    -0.07
    ίκ
    -0.07
    ीप
    -0.06
    ivicrm
    -0.06
     درخواست
    -0.06
    째
    -0.06
    Ny
    -0.06
    lexical
    -0.06
     네이트온
    -0.06
    POSITIVE LOGITS
     Savings
    0.07
     Financing
    0.07
    109
    0.07
     reducing
    0.06
     enabled
    0.06
     decades
    0.06
    _scores
    0.06
    generation
    0.06
     trolling
    0.06
     representative
    0.06
    Act Density 0.009%

    No Known Activations