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

    Neuronpedia

    INDEX
    Explanations

    Comes from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ائیو
    0.49
     sviluppo
    0.47
    ње
    0.46
    以上に
    0.46
    ᱖
    0.46
    inko
    0.46
    設け
    0.46
    linha
    0.46
     разработки
    0.46
    ริญ
    0.45
    POSITIVE LOGITS
     nac
    0.53
     matric
    0.42
     卡
    0.42
     bat
    0.41
     교
    0.41
     bust
    0.41
     바
    0.41
     Message
    0.40
     rotor
    0.40
    ährung
    0.40
    Act Density 0.001%

    No Known Activations