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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ■
    -0.08
    erior
    -0.07
     كبير
    -0.07
    Fe
    -0.07
     Yönet
    -0.07
     Purple
    -0.07
    风湿
    -0.07
    .Runtime
    -0.07
    esus
    -0.07
    怂
    -0.07
    POSITIVE LOGITS
    poll
    0.06
    .only
    0.06
    EqualityComparer
    0.06
    玃
    0.06
    的经历
    0.06
    只怕
    0.06
    ,double
    0.06
    LEVEL
    0.06
     troll
    0.06
     appare
    0.06
    Act Density 0.037%

    No Known Activations