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

    Neuronpedia

    INDEX
    Explanations

    peaks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revisar
    -0.08
    -review
    -0.08
     repetir
    -0.08
    负责
    -0.08
     제거
    -0.08
     Review
    -0.08
    负责人
    -0.07
     installment
    -0.07
     matrícula
    -0.07
    重复
    -0.07
    POSITIVE LOGITS
     bereikt
    0.09
     erreicht
    0.09
     formation
    0.09
     اهداف
    0.09
     стабиль
    0.09
    äksi
    0.08
     stabile
    0.08
     peux
    0.08
     ribbons
    0.08
    vell
    0.08
    Act Density 0.002%

    No Known Activations