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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibold
    -0.06
    tre
    -0.06
    APE
    -0.06
    Saved
    -0.06
     nhằm
    -0.06
    Enc
    -0.06
    Bạn
    -0.06
    <!--[
    -0.06
    _CALLBACK
    -0.05
    )L
    -0.05
    POSITIVE LOGITS
    osexual
    0.07
    	register
    0.06
    뉴
    0.06
    neutral
    0.06
    -path
    0.06
     pada
    0.06
    ATEGORY
    0.06
    ospital
    0.06
     paragraph
    0.06
     Updating
    0.06
    Act Density 0.001%

    No Known Activations