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

    Neuronpedia

    INDEX
    Explanations

    party affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iant
    0.89
     inhalation
    0.87
     decidedly
    0.85
    ,//
    0.84
    िता
    0.83
    വ്
    0.82
    टके
    0.81
     tenacious
    0.81
    erg
    0.80
     hoping
    0.79
    POSITIVE LOGITS
    の一
    0.83
     separado
    0.77
    udahkan
    0.75
     معا
    0.73
    acán
    0.72
    cante
    0.71
    けると
    0.70
     viaje
    0.69
     процессо
    0.68
    した場合
    0.68
    Act Density 0.000%

    No Known Activations