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

    Neuronpedia

    INDEX
    Explanations

    thermal, analysis, stability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jeh
    0.42
    玻璃
    0.41
     Solomon
    0.41
     Ahab
    0.40
    addContainer
    0.39
     Josiah
    0.39
    ガラス
    0.39
     మహి
    0.38
     glass
    0.38
    glas
    0.37
    POSITIVE LOGITS
     hyp
    0.52
     therm
    0.49
     गोवा
    0.46
     Goa
    0.44
     thermo
    0.42
    inqui
    0.42
    Anal
    0.42
     goa
    0.41
    गोवा
    0.40
    anal
    0.38
    Act Density 0.000%

    No Known Activations