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

    Neuronpedia

    INDEX
    Explanations

    institute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gender
    -0.07
    >$
    -0.06
     foes
    -0.06
     defamation
    -0.06
    遭
    -0.06
     older
    -0.05
    ocations
    -0.05
     Cyril
    -0.05
    ação
    -0.05
    ьв
    -0.05
    POSITIVE LOGITS
     Institute
    0.13
     institute
    0.12
     institutes
    0.09
     Instituto
    0.08
     Viện
    0.08
    _Report
    0.07
     programme
    0.07
    (in
    0.07
     plank
    0.07
    resolve
    0.07
    Act Density 0.009%

    No Known Activations