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

    Neuronpedia

    INDEX
    Explanations

    in-site or in-depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oea
    0.90
    𝓸
    0.80
     messed
    0.79
     gotta
    0.79
     решить
    0.78
     首先
    0.76
    ्स
    0.75
    ಸ್ಕೊ
    0.75
    atória
    0.75
    ານ
    0.75
    POSITIVE LOGITS
    のかもし
    0.82
    ter
    0.80
     چڑھ
    0.80
    ruta
    0.80
     léka
    0.79
     धोनी
    0.79
    cents
    0.78
    nurse
    0.78
    keyDown
    0.78
    Liên
    0.77
    Act Density 0.032%

    No Known Activations