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

    Neuronpedia

    INDEX
    Explanations

    life is meaningless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trent
    0.95
    ರ್ಧ
    0.73
    િય
    0.71
    writing
    0.71
    不开
    0.70
     அடுத்த
    0.70
     alpha
    0.69
    数十
    0.69
     Неза
    0.68
    alpha
    0.68
    POSITIVE LOGITS
     Ủy
    0.84
     essence
    0.83
     rejest
    0.82
     hasty
    0.81
     fruitful
    0.80
    0.80
     indeed
    0.79
     strictest
    0.78
     importantly
    0.78
     ensue
    0.78
    Act Density 0.001%

    No Known Activations