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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Driven
    -0.08
     sendData
    -0.07
     �
    -0.07
     risks
    -0.07
    $current
    -0.07
     Skipping
    -0.07
     chấp
    -0.06
    ubbo
    -0.06
     addSubview
    -0.06
    涉
    -0.06
    POSITIVE LOGITS
    成
    0.07
     impossible
    0.07
     MAS
    0.07
     האמיתי
    0.07
     få
    0.07
    ')"↵
    0.07
     forming
    0.06
    娱
    0.06
    ')}}"
    0.06
    تفاص
    0.06
    Act Density 0.106%

    No Known Activations