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

    Neuronpedia

    INDEX
    Explanations

    av

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     nằm
    -0.06
     dataType
    -0.06
    -bold
    -0.06
    耀
    -0.06
    _pan
    -0.06
     ذه
    -0.06
    جان
    -0.06
    Db
    -0.06
    ounge
    -0.06
    POSITIVE LOGITS
     ProductService
    0.09
     yapım
    0.07
     danske
    0.07
     COMM
    0.06
    _bet
    0.06
     Sox
    0.06
     cp
    0.06
    .opens
    0.06
    onet
    0.06
    -era
    0.06
    Act Density 0.004%

    No Known Activations