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

    Neuronpedia

    INDEX
    Explanations

    New Year's resolutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    송
    -0.07
    venture
    -0.07
    $info
    -0.07
     یوتی
    -0.07
     yaklaş
    -0.06
     příro
    -0.06
    (savedInstanceState
    -0.06
    anding
    -0.06
     ">
    -0.06
    modele
    -0.06
    POSITIVE LOGITS
     quieres
    0.07
     Johnny
    0.07
    Dal
    0.06
     yelling
    0.06
     HAL
    0.06
     grabbing
    0.06
    .Remove
    0.06
    契
    0.06
     Late
    0.06
    riott
    0.06
    Act Density 0.064%

    No Known Activations