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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     counterpart
    -0.08
    乃
    -0.08
     nominated
    -0.08
     challenging
    -0.08
     see
    -0.08
     mirando
    -0.08
    ’al
    -0.07
     inhabit
    -0.07
    穿
    -0.07
    েয়
    -0.07
    POSITIVE LOGITS
     VAT
    0.08
     allocations
    0.08
    ified
    0.08
     такую
    0.07
    едель
    0.07
    Соз
    0.07
    Allocate
    0.07
    allocation
    0.07
    textra
    0.07
    Argument
    0.07
    Act Density 0.001%

    No Known Activations