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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ($\
    0.46
    انيا
    0.46
     создавать
    0.43
     aforesaid
    0.42
     belanja
    0.42
    輸出
    0.41
     ~\
    0.41
     dụ
    0.41
     selfie
    0.41
     lucrat
    0.41
    POSITIVE LOGITS
    Experiment
    0.56
    Experiments
    0.56
     experiments
    0.54
     Experiment
    0.53
    Forty
    0.52
     experiment
    0.52
    Study
    0.50
     Experiments
    0.49
    Fifty
    0.49
     seventy
    0.49
    Act Density 0.002%

    No Known Activations