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

    Neuronpedia

    INDEX
    Explanations

    distance and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PushMatrix
    0.80
     Pré
    0.75
     प्री
    0.75
    hten
    0.74
     Prelude
    0.73
    ەر
    0.73
     Rend
    0.73
     running
    0.73
     race
    0.72
     Ark
    0.71
    POSITIVE LOGITS
    trip
    0.74
    Trip
    0.73
     trip
    0.71
     gegründet
    0.69
     firma
    0.68
     आंकड़ा
    0.66
     সদস্য
    0.66
    Firm
    0.65
     cifra
    0.65
     firm
    0.64
    Act Density 0.001%

    No Known Activations