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

    Neuronpedia

    INDEX
    Explanations

    data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lớp
    -0.06
    DateTime
    -0.06
     ред
    -0.06
    我的
    -0.06
    ущ
    -0.06
     γε
    -0.06
    Inserted
    -0.06
    ワ
    -0.06
     жит
    -0.06
     Kullan
    -0.06
    POSITIVE LOGITS
    ollapse
    0.07
    ("<?
    0.06
     onload
    0.06
    	http
    0.06
    ptides
    0.06
    secured
    0.06
    IES
    0.06
    resizing
    0.06
    .glob
    0.06
    ?.
    0.06
    Act Density 0.009%

    No Known Activations