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

    Neuronpedia

    INDEX
    Explanations

    the ending "-ating"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	settings
    -0.07
    competition
    -0.07
    $p
    -0.06
     incentive
    -0.06
    ifetime
    -0.06
    onclick
    -0.06
     outfit
    -0.06
    ,↵↵↵
    -0.06
    Paragraph
    -0.06
     कट
    -0.06
    POSITIVE LOGITS
    сам
    0.07
    Bon
    0.07
     ท
    0.06
    ваются
    0.06
    �
    0.06
     Moh
    0.06
    Moh
    0.06
    /F
    0.06
     MAR
    0.06
     estimator
    0.06
    Act Density 0.001%

    No Known Activations