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

    Neuronpedia

    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ní
    -0.07
    ,
    -0.06
     ].
    -0.06
     strt
    -0.06
     said
    -0.06
     受
    -0.06
     surf
    -0.06
     regained
    -0.06
     Müş
    -0.06
     ben
    -0.06
    POSITIVE LOGITS
    .compress
    0.07
    ritical
    0.06
    mojom
    0.06
     pylab
    0.06
    _samples
    0.06
    -indent
    0.06
    -google
    0.06
     intr
    0.06
    @endforeach
    0.06
    岩
    0.06
    Act Density 0.012%

    No Known Activations