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

    Neuronpedia

    INDEX
    Explanations

    startup, patches, message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lán
    0.47
    0.47
    kanie
    0.46
     dentées
    0.45
    தல்
    0.45
    úan
    0.43
    ġ
    0.43
    ήμε
    0.43
     Espíritu
    0.43
    䀓
    0.42
    POSITIVE LOGITS
    market
    0.43
     scams
    0.42
    Guarantee
    0.42
     (
    0.41
    лі
    0.41
    Diane
    0.40
     sayam
    0.40
    Inspection
    0.40
     median
    0.39
    robe
    0.39
    Act Density 0.000%

    No Known Activations