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

    Neuronpedia

    INDEX
    Explanations

    readiness and anticipation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.22
    ו
    0.96
    ー
    0.87
    다
    0.86
    ers
    0.86
    er
    0.85
    ер
    0.84
    х
    0.83
    0.82
    м
    0.82
    POSITIVE LOGITS
    腺
    1.00
    НЫ
    0.99
     carcasses
    0.96
    𝖑
    0.96
    લા
    0.95
     fact
    0.89
     vultures
    0.88
     KeyError
    0.88
     superconductors
    0.87
    本発明
    0.87
    Act Density 0.166%

    No Known Activations