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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .special
    -0.07
     hostage
    -0.07
    HomeAsUp
    -0.07
    _Position
    -0.06
    ACC
    -0.06
    	graph
    -0.06
    HTML
    -0.06
    нили
    -0.06
    ure
    -0.06
     Everyone
    -0.06
    POSITIVE LOGITS
     overst
    0.06
    	yield
    0.06
     вияв
    0.06
    /************************************************************************************************
    0.06
    報
    0.06
    cot
    0.06
     /*!
    0.05
    _irq
    0.05
     navigator
    0.05
     초기
    0.05
    Act Density 0.000%

    No Known Activations