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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _news
    -0.07
     advantages
    -0.07
     Mol
    -0.07
     Valk
    -0.06
    -link
    -0.06
    (filename
    -0.06
    .link
    -0.06
     Vietnamese
    -0.06
     impass
    -0.06
    젠
    -0.06
    POSITIVE LOGITS
     которую
    0.07
    physical
    0.07
    colors
    0.07
    在家里
    0.07
     explorer
    0.07
    pected
    0.07
     ignores
    0.07
    .edit
    0.07
    二楼
    0.07
    .the
    0.07
    Act Density 0.001%

    No Known Activations