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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    825
    -0.08
     Seek
    -0.08
     palabras
    -0.07
     pulling
    -0.07
     educated
    -0.07
     prospective
    -0.07
     Jam
    -0.07
     fools
    -0.07
     sanitary
    -0.07
    ipse
    -0.07
    POSITIVE LOGITS
    oxy
    0.06
     reused
    0.06
     vyp
    0.06
    .setProperty
    0.06
     เ�
    0.06
    stackpath
    0.06
     mist
    0.06
     tied
    0.06
     stems
    0.06
     prism
    0.06
    Act Density 0.037%

    No Known Activations