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

    Neuronpedia

    INDEX
    Explanations

    Python PEP, Lua, psych

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inhibit
    0.56
     inhibiting
    0.51
     custodian
    0.51
     earthen
    0.50
     assemblage
    0.49
     inhibitory
    0.48
     activating
    0.48
     symptomatic
    0.48
     suppressing
    0.48
     lake
    0.47
    POSITIVE LOGITS
    counterx
    0.54
     Архиви
    0.52
    苒
    0.51
    ഽ
    0.48
     Emissions
    0.48
    полни
    0.48
    AYLOR
    0.47
    ভোকেট
    0.47
    ૄ
    0.46
    racción
    0.45
    Act Density 0.003%

    No Known Activations