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

    Neuronpedia

    INDEX
    Explanations

    In the last years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spying
    -0.07
    티
    -0.07
     blast
    -0.07
    UG
    -0.06
    🤫
    -0.06
    ampionship
    -0.06
     Fact
    -0.06
    魃
    -0.06
     castle
    -0.06
    callee
    -0.06
    POSITIVE LOGITS
     fácil
    0.07
    wcs
    0.07
    .effects
    0.07
    .Enum
    0.06
    出售
    0.06
    _accessible
    0.06
     diện
    0.06
    حس
    0.06
    icontrol
    0.06
    홈
    0.06
    Act Density 0.028%

    No Known Activations