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

    Neuronpedia

    INDEX
    Explanations

    physical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smaller
    0.34
    ewną
    0.34
     Ammonia
    0.33
    smaller
    0.32
     정신
    0.31
     ammonia
    0.31
     maharaja
    0.31
     inland
    0.30
     soluble
    0.30
     internally
    0.30
    POSITIVE LOGITS
    Physical
    1.04
     physical
    1.02
    physical
    0.95
     Physical
    0.94
     fysis
    0.94
     PHYSICAL
    0.93
     physicality
    0.89
     físicas
    0.87
    物理
    0.85
     물리
    0.85
    Act Density 2.004%

    No Known Activations