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

    Neuronpedia

    INDEX
    Explanations

    /en-us/ URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    En
    0.68
     EN
    0.61
     En
    0.57
     enthalpies
    0.54
    EN
    0.51
     엔
    0.50
     en
    0.49
     enf
    0.48
     Enfield
    0.48
    엔
    0.48
    POSITIVE LOGITS
    US
    0.93
     US
    0.89
    us
    0.88
     us
    0.77
     GB
    0.73
     Us
    0.64
     нас
    0.61
     gb
    0.61
    Us
    0.58
    GB
    0.58
    Act Density 0.009%

    No Known Activations