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

    Neuronpedia

    INDEX
    Explanations

    technical strings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dial
    0.58
     Application
    0.55
     application
    0.55
     accro
    0.53
     Angew
    0.53
     sincer
    0.52
     고
    0.52
     simple
    0.51
    Declare
    0.51
     maim
    0.51
    POSITIVE LOGITS
    ṗ
    0.64
    avat
    0.61
     عط
    0.60
    avatar
    0.59
    fragt
    0.58
    withProperties
    0.56
    onuclear
    0.56
    arrivals
    0.55
     druž
    0.55
    }<\
    0.55
    Act Density 0.000%

    No Known Activations