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

    Neuronpedia

    INDEX
    Explanations

    exact or precise details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ించిన
    0.57
     Avec
    0.55
     الطرف
    0.54
    :
    0.54
     Lưu
    0.53
     Probab
    0.53
     Pudding
    0.52
     Luke
    0.52
     Jax
    0.51
     العام
    0.51
    POSITIVE LOGITS
     exacta
    0.79
     dokładnie
    0.74
    exact
    0.74
    Exact
    0.74
    exactly
    0.73
     precies
    0.73
     exacte
    0.73
     EXACT
    0.72
     exact
    0.72
     exactly
    0.71
    Act Density 0.049%

    No Known Activations