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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     licences
    -0.30
    AsStream
    -0.29
     whereabouts
    -0.28
    /stretch
    -0.27
    iston
    -0.26
     Firm
    -0.25
    lettes
    -0.25
    ç¦ģåĮº
    -0.24
    PAT
    -0.24
    .addHandler
    -0.24
    POSITIVE LOGITS
     survey
    0.27
    缸
    0.27
    æĹºçĽĽ
    0.26
    ım
    0.25
    ection
    0.25
     Rud
    0.25
    éķľåŃIJ
    0.24
    æĪIJçĨŁçļĦ
    0.24
    tron
    0.24
    .entrySet
    0.24
    Act Density 0.331%

    No Known Activations