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

    Neuronpedia

    INDEX
    Explanations

    focused on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ars
    0.49
    ktron
    0.46
    joon
    0.45
    abbam
    0.44
     माप
    0.43
    aben
    0.42
    组成的
    0.41
    ugian
    0.41
    itud
    0.41
    iguation
    0.41
    POSITIVE LOGITS
    ݨ
    0.46
    Ком
    0.44
     activid
    0.44
    Об
    0.42
    DG
    0.42
    Patch
    0.42
    }}{{
    0.41
    Пер
    0.41
    Чер
    0.41
    CNN
    0.41
    Act Density 0.003%

    No Known Activations