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

    Neuronpedia

    INDEX
    Explanations

    Objective-C method introspections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     privé
    0.41
    trag
    0.38
     Sac
    0.35
     فعل
    0.35
     Yah
    0.34
     privately
    0.34
     leg
    0.33
     Ecological
    0.33
    énées
    0.33
     slate
    0.33
    POSITIVE LOGITS
    +(
    0.80
     +(
    0.80
     -(
    0.77
    -(
    0.74
     "-
    0.68
     `-
    0.66
    +(-
    0.64
    0.64
    $-(
    0.64
    .-(
    0.62
    Act Density 0.001%

    No Known Activations