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

    Neuronpedia

    INDEX
    Explanations

    Python libraries/installations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پیر
    -0.06
     suggests
    -0.06
    ніше
    -0.06
     ank
    -0.06
    Bo
    -0.06
     обст
    -0.06
    Les
    -0.06
    conomics
    -0.06
     seguir
    -0.06
     Turks
    -0.06
    POSITIVE LOGITS
    PERTY
    0.07
    loses
    0.07
    <article
    0.07
     解
    0.07
     captions
    0.07
     Environment
    0.07
     Routes
    0.07
     Score
    0.07
     cracked
    0.07
    ToSend
    0.07
    Act Density 0.019%

    No Known Activations