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

    Neuronpedia

    INDEX
    Explanations

    Comedy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gitian
    0.77
    ㈤
    0.65
     :::
    0.65
     LSTM
    0.65
     کہہ
    0.64
     ⋮
    0.62
     午前
    0.62
    려고
    0.61
    द्धांत
    0.60
     أقل
    0.60
    POSITIVE LOGITS
     concerts
    0.92
     choirs
    0.83
     orchestras
    0.81
     singers
    0.80
     pun
    0.78
     races
    0.78
    music
    0.77
    ಾರ್
    0.75
    sports
    0.75
    antes
    0.74
    Act Density 0.000%

    No Known Activations