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

    Neuronpedia

    INDEX
    Explanations

    Dutch messages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uji
    0.95
    Usu
    0.92
    Illust
    0.88
     Emp
    0.87
    ija
    0.84
    ají
    0.84
     Mujhe
    0.83
    Uz
    0.81
    Ax
    0.81
    uski
    0.80
    POSITIVE LOGITS
    p
    0.81
    ק
    0.76
    m
    0.72
     einmal
    0.70
     wp
    0.67
    appcompat
    0.67
     strcmp
    0.67
    east
    0.67
    k
    0.66
    blower
    0.65
    Act Density 0.000%

    No Known Activations