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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trek
    -0.08
    arel
    -0.07
     Berg
    -0.07
    祀
    -0.07
    {|
    -0.07
    ὶ
    -0.07
     Morales
    -0.07
     hallmark
    -0.07
     plur
    -0.07
    icals
    -0.07
    POSITIVE LOGITS
     radiation
    0.08
     dim
    0.07
     cold
    0.07
    ألع
    0.07
    ableViewController
    0.07
    imeInterval
    0.07
    .Empty
    0.07
     composition
    0.07
    а�
    0.06
     speaker
    0.06
    Act Density 0.000%

    No Known Activations