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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    declspec
    -0.07
    ipop
    -0.07
     notify
    -0.07
     pus
    -0.07
     inaccessible
    -0.07
    UniformLocation
    -0.07
     transmitted
    -0.06
    VIDEO
    -0.06
    陲
    -0.06
    histoire
    -0.06
    POSITIVE LOGITS
    牢
    0.07
    짠
    0.07
    跨
    0.07
     Stap
    0.07
     challenge
    0.07
    න
    0.07
    但她
    0.07
    dao
    0.07
    xD
    0.06
    奶
    0.06
    Act Density 0.011%

    No Known Activations