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

    Neuronpedia

    INDEX
    Explanations

    in front of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ប្រទេស
    0.60
     paréntesis
    0.58
     théorie
    0.58
    gax
    0.56
     remotely
    0.56
     Städte
    0.56
    ब्रिट
    0.56
    Weekday
    0.54
    jería
    0.54
     находя
    0.54
    POSITIVE LOGITS
     front
    1.26
    front
    1.09
     FRONT
    0.86
    フロント
    0.84
     fronts
    0.82
    Front
    0.82
    fron
    0.77
     stance
    0.74
     circles
    0.74
     Front
    0.74
    Act Density 0.045%

    No Known Activations