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

    Neuronpedia

    INDEX
    Explanations

    disregard for pain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writes
    0.45
    inoceros
    0.44
    ackerel
    0.42
    他們的
    0.42
    сё
    0.41
     attenuate
    0.41
     intermedia
    0.41
    Writes
    0.40
    RECEIVED
    0.40
     وک
    0.40
    POSITIVE LOGITS
    ր
    0.47
    |.|
    0.44
    Helper
    0.41
    త్మిక
    0.41
    ಐ
    0.41
     мәкалә
    0.40
    乱
    0.40
    ﾄ
    0.40
     Compost
    0.40
    ть
    0.39
    Act Density 0.006%

    No Known Activations