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

    Neuronpedia

    INDEX
    Explanations

    but still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     során
    0.49
    促進
    0.49
    imov
    0.48
     論
    0.46
    創意
    0.46
     கட்டமை
    0.44
     capacités
    0.44
    爭
    0.43
    மைகள்
    0.43
     प्रक्रियाओं
    0.43
    POSITIVE LOGITS
     noticeable
    0.46
     word
    0.45
     Cessna
    0.44
     conversation
    0.43
     Ethyl
    0.43
     Waterloo
    0.43
     unofficial
    0.43
     Girlfriend
    0.43
     Verdana
    0.42
     Southwestern
    0.42
    Act Density 0.039%

    No Known Activations