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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nervous
    -0.07
    ная
    -0.07
     anticipation
    -0.07
    jections
    -0.07
     fired
    -0.07
    вая
    -0.07
     İlk
    -0.06
     anticipating
    -0.06
    anf
    -0.06
     αισ
    -0.06
    POSITIVE LOGITS
     jooksul
    0.11
    	duration
    0.10
     müdd
    0.10
     기간
    0.10
     동안
    0.10
     Duration
    0.09
    期間
    0.09
     semesters
    0.09
     boyunca
    0.09
     durée
    0.09
    Act Density 0.024%

    No Known Activations