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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aristotle
    -0.07
     cot
    -0.07
     zak
    -0.07
    racak
    -0.06
    """
↵
    -0.06
     Unknown
    -0.06
    _DISK
    -0.06
    subnet
    -0.06
    (ignore
    -0.06
     Muk
    -0.06
    POSITIVE LOGITS
     span
    0.07
    store
    0.06
    Store
    0.06
    ónico
    0.06
    �
    0.06
    �
    0.06
     této
    0.06
    filme
    0.06
    dialogs
    0.06
    VES
    0.06
    Act Density 0.043%

    No Known Activations