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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SUB
    -0.10
    SUB
    -0.09
    Feder
    -0.09
    TMP
    -0.09
     мунос
    -0.09
    јав
    -0.09
    VR
    -0.09
    авно
    -0.09
    ალურ
    -0.09
    Vacc
    -0.09
    POSITIVE LOGITS
     explanation
    0.13
     explanations
    0.12
     Explanation
    0.12
     설명
    0.11
     توض
    0.10
     نک
    0.10
     perhaps
    0.10
     объяс
    0.10
    Explanation
    0.10
    解释
    0.10
    Act Density 0.033%

    No Known Activations