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

    Neuronpedia

    INDEX
    Explanations

    grey descriptive nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.97
     (!
    1.51
     ([
    1.34
     (=
    1.21
    （
    1.18
     (~
    1.13
     [
    1.11
     –
    1.09
     ((
    1.08
     (@
    1.08
    POSITIVE LOGITS
     pihaknya
    1.41
    ，“
    0.91
     seien
    0.88
     könne
    0.88
    说道
    0.88
     وقال
    0.87
    ందన్నారు
    0.87
    ፥
    0.85
    credi
    0.84
     বলেও
    0.83
    Act Density 0.016%

    No Known Activations