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

    Neuronpedia

    INDEX
    Explanations

    technology and components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mural
    -0.07
     landing
    -0.07
     reasonably
    -0.07
    �
    -0.06
    $(".
    -0.06
     '../../../../
    -0.06
     peasants
    -0.06
    번호
    -0.06
    {}{↵
    -0.06
     Occupy
    -0.06
    POSITIVE LOGITS
     système
    0.06
    concept
    0.06
     Escape
    0.06
    """↵
    0.06
     settling
    0.06
    มต
    0.06
    IER
    0.06
    xee
    0.06
    ätt
    0.06
    無しさん
    0.06
    Act Density 0.085%

    No Known Activations