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

    Neuronpedia

    INDEX
    Explanations

    legal violations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tick
    -0.08
    �
    -0.06
    plot
    -0.06
    ={↵
    -0.06
    퍄
    -0.06
     �
    -0.06
     Naughty
    -0.06
     '",
    -0.06
     Kind
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    paren
    0.08
    href
    0.07
     cru
    0.07
    回事
    0.07
    经理
    0.07
     cruise
    0.07
     recon
    0.07
    rangle
    0.07
     referencia
    0.07
    速率
    0.07
    Act Density 0.068%

    No Known Activations