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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weak
    -1.30
    weak
    -1.14
     Weak
    -1.13
     weakness
    -1.09
     weakest
    -1.06
     weaknesses
    -1.00
    Weak
    -0.96
    spots
    -0.96
     lemah
    -0.95
     weaker
    -0.93
    POSITIVE LOGITS
     orders
    0.69
     ordres
    0.59
     ordre
    0.50
     an
    0.47
    олові
    0.47
    orders
    0.45
     order
    0.45
     orde
    0.44
     órdenes
    0.41
     при
    0.41
    Act Density 0.001%

    No Known Activations