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

    Neuronpedia

    INDEX
    Explanations

    And

    np_acts-logits-general · gemini-2.5-flash-lite

    conjunction "and" linking clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    0.71
    نگ
    0.68
    с
    0.62
    ز
    0.61
    y
    0.59
    리
    0.59
    ンの
    0.58
    的
    0.56
    ing
    0.55
    युक्त
    0.55
    POSITIVE LOGITS
     for
    0.69
     אז
    0.58
    2
    0.55
     אמ
    0.55
     stardom
    0.54
     tarixi
    0.53
     זמן
    0.52
    :
    0.52
    :");
    0.52
     dimensionality
    0.52
    Act Density 0.143%

    No Known Activations