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

    Neuronpedia

    INDEX
    Explanations

    ratings adjustment after games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OW
    0.49
    Diameter
    0.46
    Reverse
    0.46
    Ξ
    0.43
    T
    0.43
    Echo
    0.42
    逆
    0.42
    Más
    0.41
    ח
    0.41
     inverse
    0.41
    POSITIVE LOGITS
    的故事
    0.50
    प्टन
    0.49
     etmiş
    0.49
     обеспечи
    0.48
    itabbo
    0.48
    getString
    0.48
     gjør
    0.47
    ümüz
    0.46
    enda
    0.46
     sorgt
    0.46
    Act Density 0.003%

    No Known Activations