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

    Neuronpedia

    INDEX
    Explanations

    sexual content or warranty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রোগী
    0.41
     distanciation
    0.40
     surgeries
    0.39
    セイ
    0.39
    ())),
    0.39
     acuity
    0.38
    ፆ
    0.37
    წინ
    0.37
     сист
    0.36
     सजा
    0.36
    POSITIVE LOGITS
    Optimizer
    0.38
    sticker
    0.38
     Zur
    0.38
    duino
    0.38
    optimizer
    0.36
    Mod
    0.36
    স্টি
    0.36
    大全
    0.36
     haut
    0.35
     añad
    0.35
    Act Density 0.000%

    No Known Activations