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

    Neuronpedia

    INDEX
    Explanations

    technical instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .trip
    -0.08
     load
    -0.07
    一季度
    -0.07
     train
    -0.07
     al
    -0.07
     on
    -0.06
     אחד
    -0.06
     tuyên
    -0.06
     veniam
    -0.06
    🕴
    -0.06
    POSITIVE LOGITS
     финансов
    0.08
    也不要
    0.08
    瀣
    0.07
     bur
    0.07
     kB
    0.07
    יישוב
    0.07
    مناطق
    0.07
     codigo
    0.07
    "h
    0.07
     continuously
    0.07
    Act Density 0.143%

    No Known Activations