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

    Neuronpedia

    INDEX
    Explanations

    Last names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flank
    -0.08
     gained
    -0.07
    .high
    -0.07
     yếu
    -0.07
     industries
    -0.07
    也同样
    -0.07
    prus
    -0.07
     inexp
    -0.07
     proclamation
    -0.06
     sofort
    -0.06
    POSITIVE LOGITS
    Ⓑ
    0.08
    핳
    0.07
    ijkl
    0.07
    почт
    0.07
    臜
    0.07
    Regarding
    0.07
    //------------------------------------------------------------------------------↵↵
    0.07
    ธนา
    0.06
    졪
    0.06
    ㊧
    0.06
    Act Density 0.091%

    No Known Activations