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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sync
    -0.06
     walk
    -0.06
    Keeping
    -0.06
    Tot
    -0.06
     Toxic
    -0.06
    .Memory
    -0.06
     turns
    -0.06
     XXX
    -0.06
     releg
    -0.06
    _iter
    -0.06
    POSITIVE LOGITS
    ”—
    0.07
    		↵↵
    0.07
     `(
    0.06
     "$
    0.06
     ${(
    0.06
    tape
    0.06
    '$
    0.06
     SAP
    0.06
    ,status
    0.06
     $
    0.06
    Act Density 0.015%

    No Known Activations