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

    Neuronpedia

    INDEX
    Explanations

    home theater experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㪯
    0.39
     ን
    0.38
    spell
    0.38
    commend
    0.38
    Lit
    0.38
    ὠ
    0.38
    தோ
    0.37
     vra
    0.37
    agel
    0.37
     படி
    0.37
    POSITIVE LOGITS
     democratization
    0.39
    إنجليزية
    0.39
     Arun
    0.38
     अरुण
    0.37
    ᱹ
    0.37
     Arnaud
    0.37
     Cil
    0.37
     snorkeling
    0.36
     Grupo
    0.36
     slower
    0.36
    Act Density 0.002%

    No Known Activations