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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Editorial
    -0.06
     Fibonacci
    -0.06
     Deng
    -0.06
     Royal
    -0.06
    гів
    -0.06
     Specific
    -0.05
     Physical
    -0.05
     arrog
    -0.05
    mercial
    -0.05
     Julius
    -0.05
    POSITIVE LOGITS
     nợ
    0.08
    ELCOME
    0.07
     wn
    0.07
    Před
    0.07
    511
    0.07
     seguridad
    0.07
     emulator
    0.07
     socks
    0.06
     kuzey
    0.06
    _____
    0.06
    Act Density 0.000%

    No Known Activations