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

    Neuronpedia

    INDEX
    Explanations

    theoretical and experimental calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xlim
    -0.08
    imore
    -0.07
     unheard
    -0.07
    힝
    -0.07
    ield
    -0.07
     showc
    -0.07
    omething
    -0.06
    acht
    -0.06
    Blocked
    -0.06
    ijd
    -0.06
    POSITIVE LOGITS
    .JPanel
    0.07
    病例
    0.07
    .Protocol
    0.07
    粘
    0.07
    -pl
    0.06
    atri
    0.06
    𝗨
    0.06
    交叉
    0.06
     Lex
    0.06
     PAT
    0.06
    Act Density 0.103%

    No Known Activations