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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contextual usage in information

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

    Code, copyright, licenses, and versions

    np_acts-logits-general · gemini-2.0-flash

    Matthias Christian Schabel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.84
    MessageOf
    -0.72
    NOPQRST
    -0.65
    رشف
    -0.64
    Amicalement
    -0.63
    PhysRevD
    -0.62
     ProtoMessage
    -0.61
     HasFactory
    -0.60
    IntoConstraints
    -0.59
     BorderSide
    -0.59
    POSITIVE LOGITS
    niosek
    0.48
    ExtendWith
    0.48
    客
    0.45
     صوتيه
    0.42
     liés
    0.42
     nakalista
    0.41
     främ
    0.41
    umumkan
    0.41
    ahy
    0.40
     كورة
    0.40
    Act Density 0.106%

    No Known Activations