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

    Neuronpedia

    INDEX
    Explanations

    joy and humor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    It
    0.45
    Κ
    0.44
    N
    0.44
     isothermal
    0.39
    CAL
    0.38
    Far
    0.38
     in
    0.38
     حکم
    0.38
    Nou
    0.38
    Lie
    0.37
    POSITIVE LOGITS
     laughing
    0.42
    да
    0.41
    ั
    0.40
    ิ
    0.39
    на
    0.38
    ية
    0.38
    ене
    0.38
     playfully
    0.38
     playful
    0.37
    -
    0.37
    Act Density 0.059%

    No Known Activations