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

    Neuronpedia

    INDEX
    Explanations

    history of item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caviar
    0.50
     w
    0.49
     macho
    0.46
     illumination
    0.45
     thorium
    0.45
     probar
    0.45
     bromide
    0.43
     resistive
    0.43
     은행
    0.43
     revert
    0.43
    POSITIVE LOGITS
    陇
    0.44
    фек
    0.42
    cel
    0.41
    Nurse
    0.41
    珩
    0.40
    BuildConfig
    0.40
    icycl
    0.39
    战场
    0.39
    见面
    0.39
    Blog
    0.39
    Act Density 0.001%

    No Known Activations