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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pd
    -0.08
     GetData
    -0.07
     Labor
    -0.07
    /find
    -0.07
     Tw
    -0.07
     SU
    -0.07
    .Common
    -0.07
    ritical
    -0.07
    テ
    -0.07
     International
    -0.07
    POSITIVE LOGITS
     Ví
    0.06
    pictureBox
    0.06
    enery
    0.05
    .he
    0.05
     Albums
    0.05
    .fromCharCode
    0.05
    ☆
    0.05
     검색
    0.05
    또
    0.05
     �
    0.05
    Act Density 0.006%

    No Known Activations