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

    Neuronpedia

    INDEX
    Explanations

    The INC suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.55
     Cal
    0.51
    a
    0.51
     Got
    0.49
    u
    0.48
    gini
    0.48
    ק
    0.48
    t
    0.47
    kov
    0.46
    ↵↵
    0.45
    POSITIVE LOGITS
     epigen
    0.56
    2
    0.55
     ၂
    0.53
    avorites
    0.53
    :
    0.53
    }">
    0.52
     bienn
    0.52
     বাঙালির
    0.52
     andre
    0.51
     기념
    0.51
    Act Density 0.000%

    No Known Activations