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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	http
    -0.07
    ，其中
    -0.06
     masks
    -0.06
     distraction
    -0.06
    icated
    -0.06
    /apt
    -0.06
    ********
    -0.06
    terminate
    -0.06
     sampled
    -0.06
    媒体
    -0.06
    POSITIVE LOGITS
    SGlobal
    0.07
     rifles
    0.07
     health
    0.06
    imap
    0.06
    egree
    0.06
    _RG
    0.06
    xBA
    0.06
    nda
    0.06
     overhaul
    0.06
     Elaine
    0.06
    Act Density 0.021%

    No Known Activations