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

    Neuronpedia

    INDEX
    Explanations

    song parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tues
    -0.07
     fuss
    -0.07
    Circle
    -0.07
     Cult
    -0.07
    一口气
    -0.07
    叙
    -0.07
    JEXEC
    -0.06
     excuses
    -0.06
    <View
    -0.06
    ']],↵
    -0.06
    POSITIVE LOGITS
    胞
    0.07
     withdrawn
    0.07
    .schedulers
    0.07
    abilidade
    0.07
    банк
    0.07
    checks
    0.06
    徜
    0.06
    andes
    0.06
    TASK
    0.06
    .po
    0.06
    Act Density 0.019%

    No Known Activations