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

    Neuronpedia

    INDEX
    Explanations

    workload

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    5
    -0.07
    ขณะ
    -0.07
    _wrong
    -0.07
    =password
    -0.07
    وضح
    -0.07
     Toastr
    -0.07
    either
    -0.07
    !',↵
    -0.06
     trading
    -0.06
    -tier
    -0.06
    POSITIVE LOGITS
    텍
    0.07
     pronunciation
    0.07
    quence
    0.07
     má
    0.07
     הית
    0.07
     Qué
    0.07
    顺着
    0.06
     ICU
    0.06
    ביץ
    0.06
     -.
    0.06
    Act Density 0.012%

    No Known Activations