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

    Neuronpedia

    INDEX
    Explanations

    assist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你的
    -0.07
     smelling
    -0.06
    306
    -0.06
    .unknown
    -0.06
    ?</
    -0.06
    -and
    -0.06
    >
    -0.06
     chambers
    -0.06
     looking
    -0.06
    903
    -0.06
    POSITIVE LOGITS
     assault
    0.07
     setuptools
    0.07
    previous
    0.07
     doma
    0.06
    ibName
    0.06
    andez
    0.06
     posix
    0.06
     Fernandez
    0.06
    ίκ
    0.06
    omid
    0.06
    Act Density 0.007%

    No Known Activations