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

    Neuronpedia

    INDEX
    Explanations

    ular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ProducesResponseType
    -0.08
     popis
    -0.07
    emax
    -0.07
    SSIP
    -0.06
    Protection
    -0.06
     потол
    -0.06
     스
    -0.06
    (load
    -0.06
     elements
    -0.06
    .evaluate
    -0.06
    POSITIVE LOGITS
     faster
    0.07
     cheaper
    0.07
     mul
    0.07
     nation
    0.06
    ker
    0.06
    COMM
    0.06
     MOR
    0.06
    玛
    0.06
     escorted
    0.06
    shore
    0.06
    Act Density 0.001%

    No Known Activations