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

    Neuronpedia

    INDEX
    Explanations

    spell and grammar checkers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Speaker
    0.43
     narrator
    0.42
     gallery
    0.40
     앞에서
    0.40
     speaker
    0.39
     musicians
    0.39
    ்த்
    0.38
     russia
    0.38
     rumor
    0.38
     musician
    0.38
    POSITIVE LOGITS
    namento
    0.41
    षित
    0.38
    Starts
    0.38
    ("@
    0.38
    路径
    0.37
    sum
    0.37
    Nama
    0.37
    okok
    0.37
    ルダー
    0.36
    ORDIN
    0.36
    Act Density 0.000%

    No Known Activations