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

    Neuronpedia

    INDEX
    Explanations

    studies showing effects and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hopefully
    0.49
     Hopefully
    0.47
    Hopefully
    0.46
     Allow
    0.42
    我们需要
    0.41
     אר
    0.41
     هنعمل
    0.40
     хотим
    0.40
     perlu
    0.39
     Screenshot
    0.38
    POSITIVE LOGITS
     studies
    0.87
    Studies
    0.81
     Studies
    0.80
     research
    0.79
     statistically
    0.78
     empirically
    0.77
    研究
    0.75
    studies
    0.75
     researchers
    0.73
     penelitian
    0.73
    Act Density 0.134%

    No Known Activations