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

    Neuronpedia

    INDEX
    Explanations

    Microsoft technologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cad
    -0.07
     magistrate
    -0.07
     inauguration
    -0.06
    confirm
    -0.06
     ___
    -0.06
     Lee
    -0.06
     Charter
    -0.06
     advocates
    -0.06
    ync
    -0.06
     Sour
    -0.06
    POSITIVE LOGITS
    -з
    0.07
    耶
    0.07
    arseille
    0.07
    .";
    0.06
    @↵↵
    0.06
     spre
    0.06
     gameState
    0.06
    :<?
    0.06
    豪
    0.06
     �
    0.06
    Act Density 0.011%

    No Known Activations