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

    Neuronpedia

    INDEX
    Explanations

    code, URLs, system commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unwelcome
    0.59
    ampton
    0.58
     setTheme
    0.57
    ucker
    0.57
    olor
    0.54
    broker
    0.53
    asar
    0.52
    väl
    0.52
    Direct
    0.51
    emon
    0.51
    POSITIVE LOGITS
     좌표
    0.65
     Tard
    0.63
     ショ
    0.61
    频
    0.60
    キュー
    0.59
     ['./
    0.59
     NDC
    0.58
    芻
    0.58
    吲
    0.57
     フランス
    0.56
    Act Density 0.001%

    No Known Activations