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

    Neuronpedia

    INDEX
    Explanations

    author fields in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atomic
    1.00
     atomic
    0.96
     атом
    0.91
    Atomic
    0.91
    原子
    0.82
     IAEA
    0.80
     原子
    0.77
     atom
    0.76
     परमाणु
    0.76
    atomic
    0.76
    POSITIVE LOGITS
    😲
    0.41
    षण
    0.38
    Pam
    0.38
    청
    0.38
     outbreak
    0.37
     Duan
    0.36
     Sebasti
    0.35
    PROVIDED
    0.35
    Cement
    0.35
    Christopher
    0.34
    Act Density 0.003%

    No Known Activations