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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.73
     ſtate
    -0.73
     houſe
    -0.70
     purpoſe
    -0.70
     itſelf
    -0.69
     leſs
    -0.66
     neutrons
    -0.66
    ſelf
    -0.65
     faſt
    -0.65
     electrons
    -0.64
    POSITIVE LOGITS
    windowFixed
    0.60
     courants
    0.58
     dégâts
    0.54
     ouvriers
    0.52
     خارجية
    0.52
     atuais
    0.51
     actuelles
    0.51
     soluzione
    0.51
     '\\;'
    0.51
     soluzioni
    0.50
    Act Density 0.002%

    No Known Activations