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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _acquire
    -0.06
    км
    -0.06
     Med
    -0.06
     ev
    -0.06
    мос
    -0.06
    .ant
    -0.06
    .linear
    -0.06
    、これ
    -0.06
    umor
    -0.05
    _an
    -0.05
    POSITIVE LOGITS
     معمول
    0.07
     kab
    0.07
     Script
    0.06
     Merlin
    0.06
    /ss
    0.06
     Quản
    0.06
     hyperlink
    0.06
     accountant
    0.06
     famille
    0.06
    ابة
    0.06
    Act Density 0.140%

    No Known Activations