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

    Neuronpedia

    INDEX
    Explanations

    image processing code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _validator
    -0.06
     kali
    -0.06
    initializer
    -0.06
     amy
    -0.06
    anca
    -0.06
    _tgt
    -0.06
    translate
    -0.06
     Advisors
    -0.06
     Laden
    -0.06
    Maria
    -0.06
    POSITIVE LOGITS
    mods
    0.07
    .readdir
    0.06
    進
    0.06
    rm
    0.06
    .blit
    0.06
     prevented
    0.06
     �
    0.06
    ，就是
    0.06
    ？↵
    0.06
    вичай
    0.06
    Act Density 0.020%

    No Known Activations