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

    Neuronpedia

    INDEX
    Explanations

    the word "target" and words that co-occur with it

    oai_token-act-pair · gemini-2.0-flash

    target

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tonsoft
    -0.56
    GetBytes
    -0.48
    omb
    -0.48
    Lähteet
    -0.43
     stej
    -0.43
    lei
    -0.42
    here
    -0.39
    圖
    -0.39
     map
    -0.39
     berbahaya
    -0.39
    POSITIVE LOGITS
     الرياضيه
    0.73
     Walkover
    0.71
     فريبيس
    0.68
    Hentet
    0.64
     дописавши
    0.63
    isContained
    0.62
    MessageOf
    0.61
    帖最后由
    0.61
     propOrder
    0.61
     wireType
    0.61
    Act Density 4.458%

    No Known Activations