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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     messing
    -0.08
     legalization
    -0.08
     jeb
    -0.08
     legalized
    -0.08
     thirds
    -0.08
     выб
    -0.08
     neoliberal
    -0.07
     tenta
    -0.07
    无限
    -0.07
     niveles
    -0.07
    POSITIVE LOGITS
     strengthen
    0.09
     esteem
    0.09
    utip
    0.08
    奋
    0.08
    /ip
    0.08
    .unit
    0.08
     strengthening
    0.07
     appreciate
    0.07
    /parser
    0.07
     haste
    0.07
    Act Density 0.008%

    No Known Activations