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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    منتدى
    -0.08
     Дан
    -0.08
    拳头
    -0.07
     ingresar
    -0.07
    麻辣
    -0.07
     podemos
    -0.07
    集装箱
    -0.07
     starring
    -0.07
    能不能
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     adversity
    0.07
    =set
    0.07
     Cure
    0.07
    0.07
    Digit
    0.06
     securely
    0.06
     ↵↵↵↵
    0.06
    ении
    0.06
    atura
    0.06
     mix
    0.06
    Act Density 0.001%

    No Known Activations