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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kar
    -0.07
     Nob
    -0.07
     Kar
    -0.07
     destroyer
    -0.07
    Scan
    -0.06
    ّا
    -0.06
    -row
    -0.06
    çois
    -0.06
    440
    -0.06
    ADF
    -0.06
    POSITIVE LOGITS
    beautiful
    0.08
     انواع
    0.07
     akşam
    0.06
    ((&___
    0.06
    .history
    0.06
    法院
    0.06
    //------------------------------------------------------------------------------------------------
    0.06
    formace
    0.06
     kişisel
    0.06
    sunuz
    0.06
    Act Density 0.037%

    No Known Activations