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
     обме
    0.41
     encaps
    0.38
     सलाहकार
    0.37
    allclasses
    0.36
    ᓄ
    0.36
    铁
    0.35
    शिंगटन
    0.35
    ık
    0.35
     информа
    0.35
     লে
    0.35
    POSITIVE LOGITS
     Lau
    0.43
    OCA
    0.40
    Leben
    0.39
    centroid
    0.38
     malt
    0.38
    jor
    0.38
    Harrison
    0.38
    Cyber
    0.37
    Phen
    0.37
     mink
    0.37
    Act Density 0.007%

    No Known Activations