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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	trigger
    -0.07
    plers
    -0.07
    ibility
    -0.06
     Still
    -0.06
     فرود
    -0.06
    PRIMARY
    -0.06
     economy
    -0.06
     Sun
    -0.06
     된
    -0.06
    coration
    -0.06
    POSITIVE LOGITS
    ऊ
    0.06
    /****************************************************************************
    0.06
    ูไ
    0.06
     underestimated
    0.06
    ects
    0.06
     ไ
    0.06
     سم
    0.06
     cuc
    0.06
    üm
    0.06
     trovare
    0.06
    Act Density 0.020%

    No Known Activations