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

    Neuronpedia

    INDEX
    Explanations

    bringing national standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erg
    0.40
     ultras
    0.40
     homologous
    0.39
    ólica
    0.38
    og
    0.38
     ult
    0.37
     ganz
    0.37
    ult
    0.36
     coc
    0.36
     headline
    0.36
    POSITIVE LOGITS
    subset
    0.46
     एनी
    0.43
    VisualStyle
    0.41
     पड़ने
    0.41
     అంబేద్కర్
    0.41
     subset
    0.41
     Русский
    0.40
     Subset
    0.40
     അടി
    0.40
    addAnimation
    0.40
    Act Density 0.000%

    No Known Activations