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

    Neuronpedia

    INDEX
    Explanations

    energy kJ/kg systems ISP component

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πάν
    0.66
    𝒆
    0.64
    ೇ
    0.62
    社会主义
    0.61
     ಮೇಲೆ
    0.60
    ถูก
    0.60
     CHP
    0.60
     dyspe
    0.60
     Aryan
    0.59
     Viruses
    0.59
    POSITIVE LOGITS
    r
    1.05
    s
    0.88
    ר
    0.87
    single
    0.85
    stakes
    0.85
    té
    0.84
    rable
    0.84
    info
    0.83
    longer
    0.82
    a
    0.81
    Act Density 0.000%

    No Known Activations