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

    Neuronpedia

    INDEX
    Explanations

    potential actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mythology
    0.44
     choreography
    0.41
     sej
    0.41
     monumental
    0.40
    🚩
    0.40
    кугӀ
    0.39
     isotropy
    0.38
     vagina
    0.38
     Drying
    0.38
     immunology
    0.38
    POSITIVE LOGITS
    only
    0.44
    о
    0.40
    裾
    0.38
    down
    0.37
    Фу
    0.37
    led
    0.37
    เมื่อ
    0.36
    л
    0.36
    楽し
    0.36
    തെന്നും
    0.35
    Act Density 0.000%

    No Known Activations