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

    Neuronpedia

    INDEX
    Explanations

    GoogleSearch: base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    many
    0.44
    ler
    0.43
    h
    0.43
    femin
    0.42
    Medit
    0.42
    modern
    0.41
    domain
    0.41
    in
    0.41
    Opp
    0.40
    blur
    0.40
    POSITIVE LOGITS
    _-
    0.41
     гэта
    0.40
    €“
    0.38
     exhausted
    0.38
     Приступљено
    0.38
    0.37
    ότη
    0.37
     IMDb
    0.36
    ᷄
    0.36
    €”
    0.35
    Act Density 0.006%

    No Known Activations