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

    Neuronpedia

    INDEX
    Explanations

    overview

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sembl
    -0.08
    禀
    -0.07
    anch
    -0.07
    偲
    -0.07
     jó
    -0.07
     serves
    -0.07
    زل
    -0.07
     נשמע
    -0.07
    thinkable
    -0.06
     conseguir
    -0.06
    POSITIVE LOGITS
    聊天
    0.08
    _paid
    0.08
     quotas
    0.07
    口头
    0.07
     غال
    0.07
     وحتى
    0.07
    .latest
    0.07
     ~/.
    0.07
    文章来源
    0.07
    ;,
    0.07
    Act Density 0.000%

    No Known Activations