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

    Neuronpedia

    INDEX
    Explanations

    evidence-based medicine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     advertising
    0.46
     Socks
    0.41
     htons
    0.41
     conscient
    0.40
     removals
    0.40
     Advertising
    0.40
     ability
    0.39
     SAW
    0.39
     anti
    0.38
     acetylene
    0.38
    POSITIVE LOGITS
    🔬
    0.50
    レシピ
    0.49
    種
    0.47
    ルダー
    0.46
     bliss
    0.46
    serie
    0.46
    品種
    0.45
    Italia
    0.45
    Ks
    0.45
     ગૃહ
    0.45
    Act Density 0.022%

    No Known Activations