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

    Neuronpedia

    INDEX
    Explanations

    no door

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …~
    -0.91
    ина
    -0.82
     Piala
    -0.81
    Exciting
    -0.81
     amigo
    -0.81
     Erzb
    -0.78
    +:
    -0.77
    ấc
    -0.77
    ???:
    -0.77
     sweeteners
    -0.76
    POSITIVE LOGITS
    Screenshot
    1.22
    pts
    1.02
    IMG
    0.99
     wouldnt
    0.96
    Which
    0.94
     couldnt
    0.86
     hw
    0.84
     другая
    0.84
    Week
    0.82
    Kami
    0.82
    Act Density 0.010%

    No Known Activations