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

    Neuronpedia

    INDEX
    Explanations

    sarcastic or humorous tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    工作的
    0.43
     Therapy
    0.42
     Leadership
    0.42
     দৌড়ে
    0.41
     Atmosphere
    0.41
     Thermodynamic
    0.40
    他说
    0.40
     PTSD
    0.40
     Dancing
    0.39
     Vocational
    0.39
    POSITIVE LOGITS
    el
    0.52
    om
    0.52
    list
    0.51
    5
    0.51
    di
    0.50
    em
    0.49
    dual
    0.49
    display
    0.49
    es
    0.47
    des
    0.46
    Act Density 0.014%

    No Known Activations