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

    Neuronpedia

    INDEX
    Explanations

    how to best support you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗂
    0.46
    ѡ
    0.44
    submenu
    0.44
    layan
    0.44
    ᔕ
    0.43
    pessoas
    0.43
    0.43
    𝓈
    0.43
     монасты
    0.43
    sala
    0.42
    POSITIVE LOGITS
    -
    0.55
     slightest
    0.48
    ه
    0.45
    Start
    0.45
     anything
    0.44
     dàn
    0.44
     Educator
    0.43
    Anything
    0.43
     dieser
    0.42
    Standard
    0.41
    Act Density 0.002%

    No Known Activations