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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adapting
    -0.07
     Pakistani
    -0.07
    KV
    -0.07
     bundan
    -0.07
    nea
    -0.06
     rise
    -0.06
     managers
    -0.06
     Revision
    -0.06
     Amerikan
    -0.06
     бли
    -0.06
    POSITIVE LOGITS
     end
    0.13
     End
    0.11
    End
    0.09
    /end
    0.08
     END
    0.07
    end
    0.07
    _End
    0.07
    END
    0.07
     ending
    0.07
    ,end
    0.07
    Act Density 0.010%

    No Known Activations