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

    Neuronpedia

    INDEX
    Explanations

    tackle the question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mont
    1.07
     Sax
    1.06
     crainte
    1.02
     posicion
    1.02
     frustration
    1.01
     frictions
    1.01
     mont
    1.00
    mont
    0.99
    Mont
    0.99
     CDN
    0.97
    POSITIVE LOGITS
    ន្
    1.32
    醒
    1.27
    sleep
    1.21
    leep
    1.19
    睡
    1.18
    நர்
    1.16
    runken
    1.15
     immortality
    1.13
    apadam
    1.12
    嗝
    1.12
    Act Density 0.189%

    No Known Activations