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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purse
    -0.07
    î
    -0.07
    ーナ
    -0.07
    ในว
    -0.07
    erva
    -0.06
    oplevel
    -0.06
    uka
    -0.06
    艾
    -0.06
     Facing
    -0.06
    SW
    -0.06
    POSITIVE LOGITS
    playlist
    0.06
     '/')
    0.06
     регули
    0.06
     všechno
    0.06
    UserInfo
    0.06
     StringComparison
    0.05
    .Millisecond
    0.05
     published
    0.05
     Chelsea
    0.05
    -proxy
    0.05
    Act Density 0.000%

    No Known Activations