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

    Neuronpedia

    INDEX
    Explanations

    levels of complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annotation
    0.52
     personalized
    0.48
     personalize
    0.47
     indicators
    0.46
     annunci
    0.46
     aumentada
    0.46
     decorations
    0.46
     nette
    0.46
     notar
    0.44
     interface
    0.43
    POSITIVE LOGITS
    ቼ
    0.45
    マジ
    0.43
    龌
    0.42
    kurs
    0.41
    okra
    0.40
    運動
    0.40
    資金
    0.39
    Rocks
    0.39
    wear
    0.39
     Geography
    0.39
    Act Density 0.003%

    No Known Activations