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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LOSS
    -0.07
    ηγ
    -0.06
    ehr
    -0.06
    енью
    -0.06
     antennas
    -0.06
     atr
    -0.06
    Reflection
    -0.06
    갈
    -0.06
     casts
    -0.06
    DAY
    -0.06
    POSITIVE LOGITS
    §ظ
    0.07
     Resolver
    0.06
    ocrisy
    0.06
    izarre
    0.06
    #
    0.06
     الحل
    0.06
    combined
    0.06
     اینکه
    0.06
     discret
    0.06
    %;">↵
    0.06
    Act Density 0.001%

    No Known Activations