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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     पश
    -0.07
    -cn
    -0.06
     �
    -0.06
    čas
    -0.06
    μένοι
    -0.06
    WidthSpace
    -0.06
     ])
    -0.06
     severity
    -0.06
     reconciliation
    -0.06
     onward
    -0.06
    POSITIVE LOGITS
    .',
    0.07
     Adds
    0.06
     موفق
    0.06
     Grade
    0.06
     filmer
    0.06
     ruku
    0.06
    (username
    0.06
     encoder
    0.06
     عبدال
    0.06
     dette
    0.06
    Act Density 0.000%

    No Known Activations