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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    haft
    -0.07
     وجه
    -0.07
    arrison
    -0.07
    _infos
    -0.07
     bool
    -0.07
     warrants
    -0.06
    _OF
    -0.06
     chỉ
    -0.06
    Bucket
    -0.06
     땅
    -0.06
    POSITIVE LOGITS
    ensions
    0.06
    ολ
    0.06
    ило
    0.06
     вищ
    0.06
    quential
    0.06
     इक
    0.06
     casc
    0.06
    ッカー
    0.06
    intendo
    0.06
    tit
    0.06
    Act Density 0.099%

    No Known Activations