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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    .isEnabled
    -0.08
     moistur
    -0.08
    慬
    -0.07
     nấu
    -0.07
    �
    -0.07
    _changed
    -0.07
    .program
    -0.07
     şarkı
    -0.07
    帳號
    -0.07
    EmailAddress
    -0.07
    POSITIVE LOGITS
    BASE
    0.07
     gf
    0.07
    By
    0.07
    🐄
    0.07
    developers
    0.07
    /libs
    0.06
     Coke
    0.06
    发展格局
    0.06
     ber
    0.06
     presentation
    0.06
    Act Density 0.103%

    No Known Activations