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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keeps
    -0.08
    EGIN
    -0.08
     endings
    -0.08
     Apollo
    -0.07
     συνέχεια
    -0.07
    gte
    -0.07
     ends
    -0.07
     الحياة
    -0.07
     straightforward
    -0.07
     ended
    -0.07
    POSITIVE LOGITS
    (before
    0.13
    before
    0.11
     antes
    0.11
    .before
    0.10
     before
    0.10
     beforehand
    0.10
    -before
    0.09
    Before
    0.09
    	before
    0.09
     sebelum
    0.09
    Act Density 0.121%

    No Known Activations