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

    Neuronpedia

    INDEX
    Explanations

    strong descriptors related to strength and power

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

    strong and powerful descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.57
    OGND
    -0.55
    carat
    -0.43
     Paglinawan
    -0.42
    EndGlobal
    -0.41
     informée
    -0.41
     AspNetCore
    -0.40
    LLocation
    -0.40
    Ember
    -0.39
     Hush
    -0.39
    POSITIVE LOGITS
    強
    1.17
    强
    1.16
    强的
    0.93
    qiang
    0.92
     强
    0.86
    強い
    0.85
    strong
    0.85
     strong
    0.85
     強
    0.84
    Strong
    0.82
    Act Density 0.006%

    No Known Activations