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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anon
    -0.27
     brow
    -0.26
     Bender
    -0.26
    nak
    -0.25
     rendre
    -0.25
    ahead
    -0.24
     Entire
    -0.24
    åĬ¡
    -0.24
    Immediate
    -0.24
    bsp
    -0.24
    POSITIVE LOGITS
    èĩªæĿ¥
    0.26
    ea
    0.26
    åĽ½å®¶éĺŁ
    0.24
    ereum
    0.23
    äºĮåįģåĽĽ
    0.23
    ressed
    0.23
     dna
    0.23
    åīįä¸ĸ
    0.23
    常çĶ¨çļĦ
    0.23
    èµ°åIJij
    0.23
    Act Density 2.395%

    No Known Activations