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

    Neuronpedia

    INDEX
    Explanations

    technical and scientific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♀
    -0.07
     обличчя
    -0.07
    ann
    -0.06
    の子
    -0.06
     их
    -0.06
     テ
    -0.06
     Decl
    -0.06
     νέ
    -0.06
     少
    -0.06
     вариант
    -0.06
    POSITIVE LOGITS
     meno
    0.07
    (cmd
    0.07
    ě
    0.07
    comma
    0.07
     querying
    0.06
    (remove
    0.06
    .initialize
    0.06
    positor
    0.06
    (Job
    0.06
    ilege
    0.06
    Act Density 0.000%

    No Known Activations