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

    Neuronpedia

    INDEX
    Explanations

    past experiences and trauma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contenders
    0.44
    filenames
    0.44
     يجب
    0.43
    ੱਸ
    0.42
    estries
    0.42
    LD
    0.42
    files
    0.41
    ayos
    0.41
    спомина
    0.41
    playlists
    0.41
    POSITIVE LOGITS
     seksual
    0.55
     blev
    0.49
     label
    0.48
     ukuran
    0.45
     bruge
    0.45
     femelle
    0.44
     Label
    0.44
     mùi
    0.43
    os
    0.42
     Denne
    0.42
    Act Density 0.003%

    No Known Activations