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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $("#"
    -0.07
     Santana
    -0.07
     Patel
    -0.06
     Napoli
    -0.06
    'an
    -0.06
     beaches
    -0.06
     하지만
    -0.06
    letic
    -0.06
    (ac
    -0.06
     Natalie
    -0.06
    POSITIVE LOGITS
    获
    0.07
    自
    0.07
    	unset
    0.07
    .Companion
    0.06
    ergic
    0.06
    _listener
    0.06
    xFE
    0.06
    ertest
    0.06
    pecial
    0.06
     roster
    0.06
    Act Density 0.004%

    No Known Activations