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

    Neuronpedia

    INDEX
    Explanations

    count

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demeanor
    -0.09
    lac
    -0.08
     LA
    -0.08
     lembr
    -0.08
     Rector
    -0.08
    пан
    -0.08
    Zeit
    -0.08
    LDAP
    -0.08
    LA
    -0.08
     والز
    -0.08
    POSITIVE LOGITS
     incorrectly
    0.10
    _duplicates
    0.09
     overly
    0.09
     unnecessarily
    0.09
     errone
    0.09
    Duplicates
    0.09
     prematurely
    0.08
     undue
    0.08
     overlapping
    0.08
     overlap
    0.08
    Act Density 0.010%

    No Known Activations