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

    Neuronpedia

    INDEX
    Explanations

    laughter and mild surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unfamiliar
    0.47
    رځ
    0.46
     trunc
    0.44
     truncate
    0.44
     shadowing
    0.43
     familiar
    0.43
     pathogen
    0.43
     isolates
    0.43
     gxh
    0.42
    sthrough
    0.42
    POSITIVE LOGITS
    Seriously
    0.99
     Seriously
    0.96
    HAHA
    0.94
    Oh
    0.92
     Oh
    0.89
     Apparently
    0.86
    seriously
    0.83
     hehe
    0.82
    Haha
    0.82
     hahaha
    0.82
    Act Density 0.167%

    No Known Activations