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

    Neuronpedia

    INDEX
    Explanations

    story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bind
    -0.07
     port
    -0.07
     kick
    -0.06
     refactor
    -0.06
     پست
    -0.06
    yellow
    -0.06
    군요
    -0.06
     archivo
    -0.06
     Economic
    -0.06
    言って
    -0.06
    POSITIVE LOGITS
    BagConstraints
    0.08
     cliffs
    0.07
    BYTE
    0.07
    (json
    0.06
    -resolution
    0.06
    .eu
    0.06
    ﻟ�
    0.06
     Toolbar
    0.06
     plaint
    0.06
    ERSIST
    0.06
    Act Density 0.119%

    No Known Activations