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

    Neuronpedia

    INDEX
    Explanations

    acquired

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     которой
    -0.07
    icans
    -0.06
    ована
    -0.06
     homosexuality
    -0.06
     caps
    -0.06
    법
    -0.06
     Parr
    -0.06
     arkadaş
    -0.06
     humans
    -0.06
    simp
    -0.06
    POSITIVE LOGITS
     Kanye
    0.07
     NL
    0.06
     sout
    0.06
     Trout
    0.06
     VERIFY
    0.06
    egrated
    0.06
     "".
    0.06
     Bel
    0.06
    .Tags
    0.06
    theValue
    0.06
    Act Density 0.000%

    No Known Activations