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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polic
    -0.06
    '),'
    -0.06
    Semaphore
    -0.06
     пози
    -0.06
    :Register
    -0.06
     спас
    -0.06
    emplace
    -0.06
    ikhail
    -0.06
     maks
    -0.06
     کرده
    -0.06
    POSITIVE LOGITS
     RL
    0.07
     GA
    0.07
     representatives
    0.07
     declaration
    0.07
     Deb
    0.07
     MES
    0.07
    ful
    0.07
    .GroupBox
    0.07
     Mirage
    0.06
    >);↵
    0.06
    Act Density 0.073%

    No Known Activations