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

    Neuronpedia

    INDEX
    Explanations

    stability and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     augue
    0.39
    تی
    0.38
    نسب
    0.37
    observable
    0.36
    提起
    0.35
     Rath
    0.35
    Botan
    0.35
     mastic
    0.34
    callback
    0.34
    новни
    0.33
    POSITIVE LOGITS
    穩定
    0.51
     stabilit
    0.50
    安定
    0.49
     instability
    0.48
     stability
    0.48
    Stability
    0.48
     stabilité
    0.47
     stable
    0.47
     Stability
    0.47
     안정
    0.47
    Act Density 0.000%

    No Known Activations