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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    看书
    -0.08
    Convention
    -0.08
     it
    -0.07
    榫
    -0.07
    Jos
    -0.07
     '{}
    -0.07
     namedtuple
    -0.06
    AMS
    -0.06
     [].
    -0.06
    IRECTION
    -0.06
    POSITIVE LOGITS
    раниц
    0.07
     checkBox
    0.06
    恐怕
    0.06
     Buying
    0.06
    ▨
    0.06
    /resources
    0.06
    ียง
    0.06
    ﭯ
    0.06
     sólo
    0.06
    ﹽ
    0.06
    Act Density 0.003%

    No Known Activations