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

    Neuronpedia

    INDEX
    Explanations

    code changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.52
     myſelf
    -1.38
     feroit
    -1.37
    tagHelperRunner
    -1.32
     itſelf
    -1.30
     Monfieur
    -1.30
     deletes
    -1.28
    verwijspagina
    -1.27
     auroit
    -1.27
     tartalomajánló
    -1.26
    POSITIVE LOGITS
     the
    1.04
     
    0.96
     "
    0.87
     all
    0.87
     a
    0.86
     (
    0.84
     “
    0.83
     in
    0.82
     and
    0.78
     on
    0.77
    Act Density 0.031%

    No Known Activations