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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜈
    -0.08
    placing
    -0.07
    ישראל
    -0.07
    MW
    -0.07
    伶
    -0.07
     inters
    -0.07
    metros
    -0.07
    żenia
    -0.07
     isol
    -0.07
     Finding
    -0.07
    POSITIVE LOGITS
    腔
    0.07
     revamped
    0.07
    为主题
    0.07
    计划
    0.07
     �
    0.06
    主题
    0.06
    .getRequest
    0.06
     reconsider
    0.06
     directives
    0.06
    收入
    0.06
    Act Density 0.011%

    No Known Activations