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

    Neuronpedia

    INDEX
    Explanations

    code or logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continental
    -0.07
    _SKIP
    -0.07
     coalition
    -0.06
    .Max
    -0.06
        		↵
    -0.06
    (container
    -0.06
     deceive
    -0.06
    メラ
    -0.06
    _rad
    -0.06
    :this
    -0.06
    POSITIVE LOGITS
    .');
    0.07
     состоя
    0.06
    clipboard
    0.06
     dreamed
    0.06
    periments
    0.06
     apartments
    0.06
     carta
    0.06
    isempty
    0.06
    ujících
    0.06
    unding
    0.06
    Act Density 0.000%

    No Known Activations