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

    Neuronpedia

    INDEX
    Explanations

    sexual assault hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁣⁣
    0.30
    <0x19>
    0.28
     سینٹی
    0.28
    ający
    0.28
     ਗਈ
    0.27
    ää
    0.26
    文学
    0.26
    ające
    0.26
    🛁
    0.26
    ्युनिकेशन
    0.26
    POSITIVE LOGITS
    -,
    0.35
     or
    0.32
    -/
    0.31
    d
    0.31
    free
    0.30
     olmayan
    0.30
    ID
    0.29
     P
    0.29
     R
    0.28
     architectures
    0.28
    Act Density 0.173%

    No Known Activations