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

    Neuronpedia

    INDEX
    Explanations

    risk and correction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instantiate
    0.45
     architekt
    0.41
    是對
    0.39
     architecture
    0.39
     Poul
    0.38
     வட
    0.38
     Inhalt
    0.38
     geotechnical
    0.38
     sechs
    0.38
     drei
    0.37
    POSITIVE LOGITS
     lows
    0.46
     கிறிஸ்துவின்
    0.44
    FPS
    0.44
    蹰
    0.42
    ebb
    0.41
    fps
    0.40
     границы
    0.39
    risk
    0.38
     highs
    0.38
    Higher
    0.38
    Act Density 0.000%

    No Known Activations