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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     पत
    -0.07
     zag
    -0.07
     jente
    -0.07
     drm
    -0.06
     mı
    -0.06
     Hogan
    -0.06
    .TAG
    -0.06
    ahat
    -0.06
    алист
    -0.06
     turns
    -0.06
    POSITIVE LOGITS
    oppable
    0.07
     backstage
    0.07
    .Selected
    0.06
     evidence
    0.06
     ineligible
    0.06
     resolving
    0.06
    .ALL
    0.06
     microphone
    0.06
     possession
    0.06
     leadership
    0.06
    Act Density 0.002%

    No Known Activations