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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     themselves
    -0.07
     ALT
    -0.07
     pot
    -0.07
     Pot
    -0.06
     arthritis
    -0.06
    larıyla
    -0.06
     hands
    -0.06
     deadline
    -0.06
     नव
    -0.06
     Languages
    -0.06
    POSITIVE LOGITS
    )?;↵
    0.07
    -song
    0.06
     кора
    0.06
    compat
    0.06
     Rencontres
    0.06
    كور
    0.06
     ANSW
    0.06
    _aligned
    0.06
     дли
    0.06
    (TEST
    0.06
    Act Density 0.009%

    No Known Activations