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

    Neuronpedia

    INDEX
    Explanations

    EXISTS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Where
    -0.07
    उन
    -0.07
    	priv
    -0.07
    connected
    -0.06
     erro
    -0.06
     Purs
    -0.06
    zure
    -0.06
    accountId
    -0.06
     hugs
    -0.06
     teardown
    -0.06
    POSITIVE LOGITS
     );
    0.06
    .Password
    0.06
    .DropTable
    0.06
    _Style
    0.06
     emotion
    0.06
     earthqu
    0.06
     info
    0.06
    esehen
    0.06
    )...
    0.06
    uyo
    0.06
    Act Density 0.002%

    No Known Activations