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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     société
    -0.07
    RGBO
    -0.07
    ağa
    -0.07
    Dating
    -0.06
    xia
    -0.06
     цар
    -0.06
    CADE
    -0.06
    Upgrade
    -0.06
     plage
    -0.06
     summary
    -0.06
    POSITIVE LOGITS
     the
    0.08
     Jens
    0.07
    .=
    0.07
     Anthony
    0.07
    ampus
    0.07
     Recorded
    0.06
     Authorities
    0.06
     ----------------------------------------------------------------------↵
    0.06
     Ju
    0.06
     sugars
    0.06
    Act Density 0.030%

    No Known Activations