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

    Neuronpedia

    INDEX
    Explanations

    authors' last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Barry
    0.25
     J
    0.25
     Robert
    0.24
    .
    0.24
     James
    0.23
    н
    0.23
     A
    0.22
     Singh
    0.22
     John
    0.22
     L
    0.22
    POSITIVE LOGITS
    bilical
    0.26
     perpend
    0.26
     marinade
    0.25
     grotes
    0.25
     inhale
    0.25
     mandib
    0.24
     tölt
    0.24
    qualiter
    0.24
     apopt
    0.24
     Sesam
    0.24
    Act Density 0.003%

    No Known Activations