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

    Neuronpedia

    INDEX
    Explanations

    resources reserves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zvý
    -0.07
    чення
    -0.07
     ओर
    -0.07
    빌
    -0.07
     majet
    -0.07
     escalated
    -0.06
     düşür
    -0.06
    適用
    -0.06
     tvrd
    -0.06
     तरफ
    -0.06
    POSITIVE LOGITS
     test
    0.07
     innov
    0.06
    stein
    0.06
    skill
    0.06
    authors
    0.06
     Fool
    0.06
     electro
    0.06
     punishment
    0.06
    Clip
    0.06
    [{
    0.06
    Act Density 0.011%

    No Known Activations