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

    Neuronpedia

    INDEX
    Explanations

    connecting applications and data across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horr
    0.52
     craz
    0.51
     obnoxious
    0.51
     prostitute
    0.51
     horrific
    0.50
     hideous
    0.50
     terrifying
    0.48
     brazen
    0.48
     violently
    0.48
     crazy
    0.47
    POSITIVE LOGITS
     nota
    0.48
     Abbreviations
    0.47
     evento
    0.47
    Component
    0.46
     कार्य
    0.46
     Appendix
    0.46
     Capabilities
    0.45
     APPENDIX
    0.45
    上一
    0.45
     Subsidi
    0.43
    Act Density 0.000%

    No Known Activations