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

    Neuronpedia

    INDEX
    Explanations

    commands and sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Voici
    0.53
     Вот
    0.52
    ：
    0.52
     다음과
    0.50
    Вот
    0.50
     şöyle
    0.48
     вот
    0.48
     here
    0.47
     voici
    0.47
     huile
    0.46
    POSITIVE LOGITS
    attacks
    0.41
    应用于
    0.40
    applied
    0.39
    attempts
    0.39
     কারণে
    0.39
    ourism
    0.39
    adjust
    0.39
    applications
    0.38
    apply
    0.38
    us
    0.38
    Act Density 0.084%

    No Known Activations