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

    Neuronpedia

    INDEX
    Explanations

    synthetic documentaries and AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    μάτων
    0.46
     rejoin
    0.46
     dodge
    0.45
     Re
    0.44
     Purchase
    0.44
     Reload
    0.44
     reload
    0.44
     waive
    0.44
     Dinge
    0.43
     deny
    0.43
    POSITIVE LOGITS
    specifically
    0.52
    oved
    0.46
    केट
    0.46
    сто
    0.45
    টাল
    0.44
    டையாக
    0.43
    nrB
    0.43
    ärt
    0.42
    ür
    0.42
    льно
    0.41
    Act Density 0.000%

    No Known Activations