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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     民
    -0.07
    ча
    -0.06
     whip
    -0.06
    公園
    -0.06
    نى
    -0.06
    nob
    -0.06
    (round
    -0.06
    wood
    -0.06
    learner
    -0.06
    ича
    -0.06
    POSITIVE LOGITS
    lıklar
    0.07
     corrupted
    0.07
    εύ
    0.07
    .future
    0.07
    	RTLI
    0.07
     reco
    0.06
    .Customer
    0.06
    imonial
    0.06
    MSN
    0.06
    -calendar
    0.06
    Act Density 0.016%

    No Known Activations