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

    Neuronpedia

    INDEX
    Explanations

    General article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ازل
    -0.06
    Tree
    -0.06
    014
    -0.06
     overflowing
    -0.06
    _mysql
    -0.06
     thinker
    -0.06
     HH
    -0.06
     didSet
    -0.06
     exhibit
    -0.06
     XHTML
    -0.06
    POSITIVE LOGITS
    打
    0.07
     neust
    0.07
     де
    0.06
    (tokens
    0.06
    REFER
    0.06
    聚
    0.06
     Lak
    0.06
    τές
    0.06
     Leak
    0.06
     challeng
    0.06
    Act Density 0.102%

    No Known Activations