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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()
    0.51
     humanities
    0.50
     could
    0.49
     humans
    0.49
     coffee
    0.49
     schedule
    0.48
     Crowley
    0.48
     desire
    0.47
     hydroelectric
    0.47
    =""
    0.46
    POSITIVE LOGITS
    ροσ
    0.47
    infs
    0.46
    たくさんの
    0.46
     andRow
    0.46
    oreg
    0.45
    σκε
    0.45
    Як
    0.44
    她的
    0.44
    ifers
    0.44
    Spots
    0.44
    Act Density 0.000%

    No Known Activations