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

    Neuronpedia

    INDEX
    Explanations

    asking for a joke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പാല
    0.77
    enthic
    0.72
    缎
    0.72
     घालून
    0.71
     കാലാവ
    0.68
    Chem
    0.68
    cosystem
    0.66
    uv
    0.66
    甸
    0.65
    chdir
    0.63
    POSITIVE LOGITS
     humorous
    3.80
     jokes
    3.80
     humor
    3.79
     joke
    3.74
     comedic
    3.70
     comedy
    3.61
     hilarious
    3.54
     humour
    3.46
     funny
    3.30
     Humor
    3.26
    Act Density 1.069%

    No Known Activations