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

    Neuronpedia

    INDEX
    Explanations

    approximations or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geiger
    0.48
     Perspekt
    0.46
     Perspective
    0.43
     Organization
    0.42
     perspectives
    0.40
    thirds
    0.40
    Perspective
    0.40
    مركز
    0.40
    ಾಣ
    0.40
    完整
    0.39
    POSITIVE LOGITS
     Screens
    0.41
    uni
    0.41
     senang
    0.38
    aly
    0.38
    nett
    0.37
     yam
    0.37
    illi
    0.37
     অক্ষ
    0.37
     heed
    0.37
    screens
    0.36
    Act Density 0.000%

    No Known Activations