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

    Neuronpedia

    INDEX
    Explanations

    comparison, ease, speed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endoth
    -0.07
    restrict
    -0.07
     GL
    -0.07
    enheim
    -0.06
     incapac
    -0.06
    resenter
    -0.06
    .Exception
    -0.06
     regulate
    -0.06
     yields
    -0.06
     INSTANCE
    -0.06
    POSITIVE LOGITS
     klein
    0.06
    حق
    0.06
    帽
    0.06
    อนท
    0.06
    องท
    0.06
    ;br
    0.06
     espan
    0.06
    ippets
    0.06
    )did
    0.06
    息
    0.06
    Act Density 0.213%

    No Known Activations