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

    Neuronpedia

    INDEX
    Explanations

    frustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     especial
    0.40
    AID
    0.37
    "=
    0.35
    iffe
    0.35
    <unused82>
    0.34
    propto
    0.34
     الهدف
    0.34
    ঝো
    0.34
    GraphQl
    0.34
    <unused539>
    0.34
    POSITIVE LOGITS
     फ्र
    0.74
     fr
    0.73
     Fr
    0.71
    Fr
    0.69
     frag
    0.66
     FR
    0.62
     ফ্র
    0.62
     Fraser
    0.60
     Fridays
    0.58
     فر
    0.57
    Act Density 0.041%

    No Known Activations