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

    Neuronpedia

    INDEX
    Explanations

    statistical data and estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ableConcept
    0.46
    பந்த
    0.45
     fonctionnal
    0.45
     Workflow
    0.44
     Fähigkeiten
    0.44
    نام
    0.43
     અનુભ
    0.43
     เหมาะ
    0.43
    风格
    0.41
    场景
    0.40
    POSITIVE LOGITS
     statistics
    1.86
     numbers
    1.77
     chiffres
    1.68
     cifras
    1.65
    statistics
    1.59
    numbers
    1.54
     statistic
    1.54
     estimates
    1.50
     stats
    1.50
     statistik
    1.50
    Act Density 0.085%

    No Known Activations