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

    Neuronpedia

    INDEX
    Explanations

    suicide conversation safety response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    green
    0.45
    scroll
    0.45
    Insights
    0.43
    ww
    0.43
    awa
    0.42
    way
    0.42
    -
    0.42
    wie
    0.41
    Fro
    0.41
    fire
    0.41
    POSITIVE LOGITS
     Stef
    0.54
    老師
    0.51
     규칙
    0.48
     apnea
    0.46
     alimentar
    0.46
    刺繍
    0.45
     Embro
    0.44
     disput
    0.43
     embro
    0.43
    ន្ទ
    0.43
    Act Density 0.002%

    No Known Activations