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

    Neuronpedia

    INDEX
    Explanations

    credentials that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    妠
    0.43
    jego
    0.42
    गिरी
    0.42
    ódromo
    0.41
    圾
    0.41
    䆔
    0.41
     सुनेंरोक
    0.40
    გუფი
    0.39
    reciate
    0.39
    加坡
    0.38
    POSITIVE LOGITS
     increasing
    0.39
     juu
    0.38
     Increasing
    0.38
     filth
    0.37
     narration
    0.36
     dam
    0.36
     Jews
    0.36
    かつ
    0.36
     Nova
    0.35
     NOVA
    0.35
    Act Density 0.000%

    No Known Activations