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

    Neuronpedia

    INDEX
    Explanations

    domestic violence hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AllCaps
    0.70
     ал
    0.67
     ALE
    0.67
     Али
    0.67
     Lynd
    0.65
    čius
    0.64
     Alfred
    0.64
    alti
    0.63
     Al
    0.63
    ̡
    0.62
    POSITIVE LOGITS
    χε
    0.62
     Rod
    0.61
    gani
    0.59
     bon
    0.58
    geme
    0.58
     gering
    0.57
    experimental
    0.56
     Experimental
    0.56
     στρα
    0.55
     experimental
    0.54
    Act Density 0.108%

    No Known Activations