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

    Neuronpedia

    INDEX
    Explanations

    numbers in brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nano
    0.37
     Donor
    0.36
     mango
    0.35
     raffle
    0.34
     nanoparticle
    0.33
     will
    0.33
     Realt
    0.33
     Dimensional
    0.33
     bottoms
    0.32
     Creo
    0.32
    POSITIVE LOGITS
    eningrad
    0.39
    ivasena
    0.37
    including
    0.36
    byterian
    0.36
     しかし
    0.35
    しかし
    0.35
    آ
    0.35
     تاہم
    0.35
    كتب
    0.34
    されます
    0.34
    Act Density 0.001%

    No Known Activations