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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dorsal
    -0.07
    >f
    -0.07
    ，便
    -0.07
    ，用
    -0.07
     zi
    -0.06
     locus
    -0.06
     vertical
    -0.06
    _unit
    -0.06
    ksi
    -0.06
    ocene
    -0.06
    POSITIVE LOGITS
    .Red
    0.06
     nového
    0.06
    TECTED
    0.06
     воз
    0.06
    №№№№
    0.06
    =\'
    0.06
     النس
    0.06
    		    ↵
    0.06
    这些
    0.06
    وير
    0.06
    Act Density 0.014%

    No Known Activations