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

    Neuronpedia

    INDEX
    Explanations

    log levels and appenders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    記録
    0.46
    次的
    0.45
    Histor
    0.45
     analyt
    0.44
    記錄
    0.41
    streak
    0.40
    Analytics
    0.40
    Turn
    0.39
     기록
    0.39
    ارية
    0.39
    POSITIVE LOGITS
    spacePad
    0.51
    layouts
    0.47
     Rolling
    0.46
     Layout
    0.43
     layout
    0.43
    append
    0.41
     Rol
    0.41
     gro
    0.41
     rolling
    0.41
     roller
    0.40
    Act Density 0.006%

    No Known Activations