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

    Neuronpedia

    INDEX
    Explanations

    proxy friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mappings
    0.41
     Cari
    0.41
     Chilean
    0.38
    BUCK
    0.36
    슭
    0.36
     masing
    0.36
     Plex
    0.36
     mapp
    0.36
     Gabriel
    0.36
     alun
    0.36
    POSITIVE LOGITS
    偃
    0.45
     الاش
    0.44
    זר
    0.43
    ciences
    0.43
    avad
    0.42
    iftoire
    0.40
    टीन
    0.39
    ົດ
    0.39
    óa
    0.37
    Mve
    0.37
    Act Density 0.000%

    No Known Activations