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

    Neuronpedia

    INDEX
    Explanations

    phrase completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flowLayoutPanel
    0.55
     नदियों
    0.54
     મતદાન
    0.53
    n
    0.52
     Balliye
    0.51
     සම්බන්ධ
    0.51
     deviate
    0.50
    dyl
    0.49
     afectada
    0.46
     резулта
    0.46
    POSITIVE LOGITS
     tasting
    0.45
    ोर्ट
    0.44
     therapist
    0.44
     ===
    0.43
    ijker
    0.42
     intro
    0.41
     detailed
    0.40
     schematic
    0.40
    Saver
    0.39
     debugging
    0.38
    Act Density 0.000%

    No Known Activations