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

    Neuronpedia

    INDEX
    Explanations

    Application outcome notifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     applicant
    -0.07
     popcorn
    -0.06
    Division
    -0.06
     theatre
    -0.06
     Av
    -0.06
     husbands
    -0.06
     distance
    -0.06
     states
    -0.06
     dental
    -0.06
    (artist
    -0.06
    POSITIVE LOGITS
     Edited
    0.06
    itelist
    0.06
    417
    0.06
     iNdEx
    0.06
     клет
    0.06
     良
    0.06
     언
    0.06
    endment
    0.06
     Kitt
    0.06
    ünden
    0.06
    Act Density 0.015%

    No Known Activations