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

    Neuronpedia

    INDEX
    Explanations

    pet ownership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gods
    -0.07
    protocol
    -0.07
    Semaphore
    -0.07
    avan
    -0.07
    lane
    -0.07
    low
    -0.07
    โก
    -0.06
    _dic
    -0.06
    errno
    -0.06
    _net
    -0.06
    POSITIVE LOGITS
     injured
    0.07
     cle
    0.06
    darwin
    0.06
     Ί
    0.06
     Daisy
    0.06
    .dest
    0.06
    ][:
    0.06
    ]])↵
    0.06
    }?
    0.06
     embarrassment
    0.06
    Act Density 0.081%

    No Known Activations