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

    Neuronpedia

    INDEX
    Explanations

    4/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instantaneous
    0.43
    Sleep
    0.39
     nocturnal
    0.39
    Instant
    0.38
    inston
    0.38
    циони
    0.38
    Hrs
    0.38
     활동
    0.37
     hasty
    0.37
     aktive
    0.37
    POSITIVE LOGITS
     Haley
    0.37
     чаще
    0.36
    ılığı
    0.36
    🏳
    0.36
    itely
    0.36
    攜
    0.36
     पुरा
    0.35
    堌
    0.35
     రాయ
    0.35
    cano
    0.35
    Act Density 0.001%

    No Known Activations