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

    Neuronpedia

    INDEX
    Explanations

    case studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    trash
    0.46
    čkog
    0.45
    ökk
    0.45
     Phú
    0.43
    the
    0.41
    unnumbered
    0.41
    <h6>
    0.41
    ്ര
    0.41
    ského
    0.41
    <h5>
    0.40
    POSITIVE LOGITS
    Case
    0.98
     Case
    0.92
    case
    0.80
    Cases
    0.79
     Cases
    0.78
     cases
    0.78
     case
    0.77
     CASE
    0.73
    CASE
    0.72
    ケース
    0.68
    Act Density 0.013%

    No Known Activations