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

    Neuronpedia

    INDEX
    Explanations

    well and commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UDGE
    -0.07
     Returns
    -0.07
    uard
    -0.07
    words
    -0.07
     hosts
    -0.07
    /find
    -0.06
    霖
    -0.06
    第
    -0.06
    Ր
    -0.06
     January
    -0.06
    POSITIVE LOGITS
    تحليل
    0.07
     aplic
    0.07
    __.'/
    0.07
     riff
    0.07
    locking
    0.07
     envelopes
    0.06
     incontri
    0.06
    .Currency
    0.06
    されていた
    0.06
    лемент
    0.06
    Act Density 0.162%

    No Known Activations