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

    Neuronpedia

    INDEX
    Explanations

    Llama models, fine-tuning, and text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allen
    0.45
     pinturas
    0.45
     feste
    0.45
    версите
    0.45
     circunstancias
    0.44
     मानदंडों
    0.44
    cary
    0.44
     მნიშვნელ
    0.44
     Hall
    0.43
     Este
    0.43
    POSITIVE LOGITS
    发动机
    0.45
    ást
    0.44
     uploading
    0.44
    OnUiThread
    0.44
     stripped
    0.44
    stripped
    0.41
    エンジン
    0.41
     downloading
    0.40
    ゔ
    0.40
     onChanged
    0.40
    Act Density 0.001%

    No Known Activations