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

    Neuronpedia

    INDEX
    Explanations

    code configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .xrLabel
    -0.07
    vail
    -0.06
     결과
    -0.06
     brow
    -0.06
     сообщ
    -0.06
    election
    -0.06
     Гол
    -0.06
     districts
    -0.06
    ial
    -0.06
     landmark
    -0.06
    POSITIVE LOGITS
    सभ
    0.06
    .Free
    0.06
    ुरक
    0.06
    harga
    0.06
    upiter
    0.06
     misogyn
    0.06
     Kos
    0.06
    malı
    0.06
    사업
    0.06
    있는
    0.06
    Act Density 0.025%

    No Known Activations