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

    Neuronpedia

    INDEX
    Explanations

    placeholder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     закін
    -0.07
    ленный
    -0.07
     enjoyable
    -0.06
    brero
    -0.06
     documented
    -0.06
     disconnected
    -0.06
    PosY
    -0.06
     jub
    -0.06
    (enc
    -0.06
    kit
    -0.06
    POSITIVE LOGITS
     placeholder
    0.21
     placeholders
    0.14
    	placeholder
    0.13
     metavar
    0.08
    он
    0.07
    Places
    0.07
    Pr
    0.07
    .isArray
    0.07
     Regional
    0.06
     propTypes
    0.06
    Act Density 0.002%

    No Known Activations