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
    tuk
    -0.07
    While
    -0.06
     Configure
    -0.06
     adamant
    -0.06
    .series
    -0.06
    .notifyDataSetChanged
    -0.06
    朱
    -0.06
     dl
    -0.06
    .Real
    -0.06
     coer
    -0.06
    POSITIVE LOGITS
    #=
    0.07
    Ш
    0.07
     。↵
    0.07
    辞
    0.06
    **:
    0.06
     \
    0.06
     Diabetes
    0.06
     expert
    0.06
    ormal
    0.06
    ###↵↵
    0.06
    Act Density 0.123%

    No Known Activations