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

    Neuronpedia

    INDEX
    Explanations

    Angle brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aw
    -0.06
    licant
    -0.06
    ?=
    -0.06
     prose
    -0.06
     pok
    -0.06
    finder
    -0.06
    -expand
    -0.06
     Replica
    -0.06
     nombres
    -0.06
    -db
    -0.06
    POSITIVE LOGITS
     Jacksonville
    0.06
    agenda
    0.06
    ुगत
    0.06
     Gross
    0.06
    )';↵
    0.06
    .done
    0.06
     рівня
    0.06
    (quantity
    0.06
    	expected
    0.06
    ransition
    0.06
    Act Density 0.015%

    No Known Activations