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

    Neuronpedia

    INDEX
    Explanations

    programming commands and output

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    command line execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.50
     pleaſure
    -0.49
    ConstraintMaker
    -0.45
     ſen
    -0.43
     ſel
    -0.40
    новништво
    -0.38
     Reſ
    -0.38
     eſſ
    -0.38
     tranſ
    -0.38
     Monfieur
    -0.38
    POSITIVE LOGITS
    "}")
    0.50
    󠁴
    0.49
    ลอง
    0.49
     plugged
    0.47
    }>;
    0.47
     tinggal
    0.46
    ndra
    0.46
     wystarczy
    0.45
     plugging
    0.45
    LabelTagHelper
    0.45
    Act Density 0.256%

    No Known Activations