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

    Neuronpedia

    INDEX
    Explanations

    width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     труда
    -0.07
     Gaga
    -0.07
    如何
    -0.06
    áp
    -0.06
     llama
    -0.06
     Meal
    -0.06
     Elim
    -0.06
    вищ
    -0.06
    bild
    -0.06
     Persona
    -0.06
    POSITIVE LOGITS
    cantidad
    0.07
    -length
    0.07
    /bower
    0.07
    Aws
    0.07
    ¼
    0.06
     intrigue
    0.06
     gain
    0.06
    ！");↵
    0.06
    agrant
    0.06
    setCurrent
    0.06
    Act Density 0.003%

    No Known Activations