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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    736
    -0.07
     isSuccess
    -0.07
    队
    -0.07
     (!((
    -0.06
     определен
    -0.06
    ****/↵
    -0.06
     erased
    -0.06
    .birth
    -0.06
     mouseClicked
    -0.06
     exam
    -0.06
    POSITIVE LOGITS
     THEY
    0.07
     McD
    0.06
     Domino
    0.06
     Decom
    0.06
    aleur
    0.06
    slice
    0.06
    タル
    0.06
     Rockets
    0.06
    chez
    0.06
    Panel
    0.06
    Act Density 0.008%

    No Known Activations