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

    Neuronpedia

    INDEX
    Explanations

    'IB' folder context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಿಸ್ಟ
    1.05
     eagerness
    1.05
     eager
    1.02
    가
    0.96
     endearing
    0.95
    istant
    0.93
    ή
    0.91
    ሲ
    0.90
     books
    0.90
    HY
    0.89
    POSITIVE LOGITS
    uleiro
    1.32
    onucle
    1.24
     ovip
    1.20
     scrat
    1.16
     Herstellung
    1.13
     воздей
    1.11
     barb
    1.09
    wort
    1.09
    amate
    1.08
    lions
    1.07
    Act Density 0.001%

    No Known Activations