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

    Neuronpedia

    INDEX
    Explanations

    navigation and to go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fread
    0.66
    ارم
    0.65
    arle
    0.63
    aard
    0.61
     चमत्कार
    0.60
    ताज
    0.59
     stuffed
    0.58
     incul
    0.57
     remplir
    0.57
    ріа
    0.57
    POSITIVE LOGITS
    goto
    2.23
     going
    2.13
     pergi
    2.12
     goto
    2.08
     Going
    2.00
     went
    1.99
     goes
    1.89
    Going
    1.88
    ໄປ
    1.88
     Went
    1.86
    Act Density 0.100%

    No Known Activations