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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     angles
    -0.06
    .Commands
    -0.06
    &W
    -0.06
    uyễn
    -0.06
     Mej
    -0.06
     루
    -0.06
     desar
    -0.06
    NonNull
    -0.05
    .hist
    -0.05
    -help
    -0.05
    POSITIVE LOGITS
     virgin
    0.07
    ์ได
    0.07
     zosta
    0.06
     lok
    0.06
     Ov
    0.06
    .").
    0.06
    tractor
    0.06
    .FileWriter
    0.06
     kork
    0.06
    .:
    0.06
    Act Density 0.023%

    No Known Activations