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

    Neuronpedia

    INDEX
    Explanations

    gunpowder, bid, selling, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    0.50
    vis
    0.49
     stress
    0.46
    man
    0.46
    form
    0.44
    yn
    0.44
    S
    0.44
    र्‍या
    0.42
     fabric
    0.42
    Fabric
    0.41
    POSITIVE LOGITS
    ڕۆ
    0.59
    拶
    0.57
     முக்கியமான
    0.55
     Ио
    0.54
     incertid
    0.54
    ک
    0.54
     〢
    0.54
     լ
    0.53
     इंटे
    0.53
     Einstellungen
    0.53
    Act Density 0.000%

    No Known Activations