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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Forward
    -0.07
    发送
    -0.06
     Anc
    -0.06
    ีม
    -0.06
    Sr
    -0.06
     kne
    -0.06
    Assigned
    -0.06
     tear
    -0.06
    亚
    -0.06
    .standard
    -0.06
    POSITIVE LOGITS
     İstanbul
    0.07
     Pdf
    0.07
     повинна
    0.06
     /*
↵
    0.06
     당시
    0.06
     <$>
    0.06
    _DYNAMIC
    0.06
    igaret
    0.06
     بنا
    0.06
    _REC
    0.06
    Act Density 0.016%

    No Known Activations