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

    Neuronpedia

    INDEX
    Explanations

    Code/programming snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stern
    -0.07
    iore
    -0.06
    enate
    -0.06
    Dal
    -0.06
    erving
    -0.06
    Omega
    -0.06
    brate
    -0.06
    ν
    -0.06
     SND
    -0.06
    σμ
    -0.06
    POSITIVE LOGITS
    　 　 　 　 　
    0.07
    (jsonPath
    0.07
     starter
    0.06
    �
    0.06
     congrat
    0.06
     препара
    0.06
     Nội
    0.06
    大全
    0.06
     recruited
    0.06
    OTOS
    0.06
    Act Density 0.355%

    No Known Activations