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

    Neuronpedia

    INDEX
    Explanations

    members

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infancy
    -0.07
    ociety
    -0.06
    Precio
    -0.06
     optical
    -0.06
     форма
    -0.06
     cw
    -0.06
    _HEALTH
    -0.06
    /action
    -0.06
    android
    -0.06
     diagnostics
    -0.06
    POSITIVE LOGITS
    Members
    0.08
    imde
    0.07
     members
    0.07
     niệm
    0.07
     teammates
    0.07
     %↵
    0.07
    undler
    0.07
    -vesm
    0.07
     Moder
    0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.07
    Act Density 0.010%

    No Known Activations