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

    Neuronpedia

    INDEX
    Explanations

    cold followed by dread

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    1.06
    도
    1.04
    ה
    0.96
    ות
    0.95
    も
    0.95
    ک
    0.91
    ла
    0.91
    리
    0.90
    נו
    0.88
    茷
    0.87
    POSITIVE LOGITS
     frío
    1.52
    Cold
    1.38
     frio
    1.38
    cold
    1.32
     cold
    1.27
    冷
    1.18
     colder
    1.13
     Cold
    1.12
     soğ
    1.11
    AY
    1.05
    Act Density 0.026%

    No Known Activations