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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ورت
    -0.07
     Comput
    -0.06
     items
    -0.06
    Orden
    -0.06
     Melanie
    -0.06
    Greg
    -0.06
     redhead
    -0.06
     iT
    -0.05
     entreg
    -0.05
     Rita
    -0.05
    POSITIVE LOGITS
    pluck
    0.07
    айт
    0.07
     UPLOAD
    0.07
    roots
    0.07
    �
    0.07
    [js
    0.07
     “[
    0.07
     участь
    0.07
     хви
    0.07
    mal
    0.07
    Act Density 0.046%

    No Known Activations