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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    间
    -0.07
    уста
    -0.07
     comforts
    -0.07
    егда
    -0.07
     voksne
    -0.07
    ії
    -0.07
    .isDefined
    -0.06
    ])[
    -0.06
     inquire
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     Wins
    0.07
     averaging
    0.06
    .lin
    0.06
     slash
    0.06
     from
    0.06
     UClass
    0.06
     MIDI
    0.06
    NullException
    0.06
     midterm
    0.06
     пері
    0.06
    Act Density 0.066%

    No Known Activations