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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    访
    -0.30
    fav
    -0.28
    çķ¹
    -0.26
     empt
    -0.25
     Foley
    -0.25
     happen
    -0.24
    elin
    -0.24
    CLA
    -0.24
    -law
    -0.24
    Plate
    -0.24
    POSITIVE LOGITS
    antly
    0.28
    乩
    0.27
    é«ĺçŃī
    0.25
     planta
    0.25
     beats
    0.24
    åĬ©
    0.24
     cheaper
    0.24
    棵æłij
    0.24
    MDB
    0.24
    æ¤į
    0.23
    Act Density 0.014%

    No Known Activations