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

    Neuronpedia

    INDEX
    Explanations

    site locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irit
    -0.07
     initialization
    -0.07
    ిత
    -0.07
    ಿತ
    -0.07
    িতা
    -0.07
    ിത്ത
    -0.07
    fake
    -0.07
    ng
    -0.07
    کز
    -0.07
    ்ந்த
    -0.07
    POSITIVE LOGITS
     Plum
    0.08
     práctico
    0.08
     продукции
    0.08
     Evidence
    0.08
     Prompt
    0.08
     Schn
    0.07
     Plot
    0.07
     Practical
    0.07
     Steck
    0.07
    Plot
    0.07
    Act Density 0.001%

    No Known Activations