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

    Neuronpedia

    INDEX
    Explanations

    directly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gerr
    -0.27
    nav
    -0.26
    -Class
    -0.26
     inv
    -0.25
    å®ŀä½ĵ
    -0.25
    oha
    -0.25
    abs
    -0.24
    åıĭ们
    -0.24
    ória
    -0.24
    äºı
    -0.24
    POSITIVE LOGITS
    rollable
    0.26
    estone
    0.26
    ingen
    0.25
     conception
    0.24
     decking
    0.24
    amiento
    0.23
     поб
    0.23
    ä¸Ģ棵
    0.23
    ç½®ä¸ļ
    0.23
    å°ijè§ģ
    0.23
    Act Density 9.086%

    No Known Activations