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

    Neuronpedia

    INDEX
    Explanations

    satisfaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ổ
    -0.07
     '@
    -0.07
    ♁
    -0.07
     Elemental
    -0.07
    urgent
    -0.07
    adjusted
    -0.07
    ও
    -0.06
     Advisory
    -0.06
    \Extension
    -0.06
    erner
    -0.06
    POSITIVE LOGITS
     즉
    0.08
    takes
    0.07
     methodology
    0.07
     sanitizer
    0.07
    吗
    0.07
    她在
    0.07
    0.07
     bias
    0.07
     żeby
    0.07
     Mits
    0.07
    Act Density 0.012%

    No Known Activations