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

    Neuronpedia

    INDEX
    Explanations

    Video content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æ³®
    -0.32
     Spit
    -0.28
    dig
    -0.28
    åĵı
    -0.27
     resil
    -0.26
    vided
    -0.26
    .Lookup
    -0.25
    äºıæįŁ
    -0.25
    æŀª
    -0.25
    actor
    -0.25
    POSITIVE LOGITS
    æijŀ
    0.27
     bordel
    0.26
     Arr
    0.25
    hem
    0.25
    áo
    0.25
    YN
    0.24
     Elect
    0.24
    å®īæİĴ
    0.24
    åıł
    0.24
    unan
    0.24
    Act Density 0.734%

    No Known Activations