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

    Neuronpedia

    INDEX
    Explanations

    marking, tagging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erect
    -0.06
    ritic
    -0.06
    elled
    -0.06
    ider
    -0.06
     islands
    -0.06
    heads
    -0.06
    faq
    -0.06
    	hs
    -0.06
    _magic
    -0.06
     Isis
    -0.06
    POSITIVE LOGITS
    ยนแปลง
    0.07
    @SuppressWarnings
    0.07
    .decoder
    0.06
     taxable
    0.06
     Krish
    0.06
     molto
    0.06
    คโน
    0.06
    第四
    0.06
    [source
    0.06
     Perr
    0.06
    Act Density 0.033%

    No Known Activations