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

    Neuronpedia

    INDEX
    Explanations

    pretend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fight
    -0.07
     readily
    -0.07
     پرداخت
    -0.06
     systemic
    -0.06
    ovie
    -0.06
     역시
    -0.06
    �
    -0.06
     Flush
    -0.06
    :.:.:
    -0.06
    xor
    -0.06
    POSITIVE LOGITS
    .frame
    0.07
    >'.↵
    0.06
    [List
    0.06
    Url
    0.06
     dormant
    0.06
    .pan
    0.06
     California
    0.06
    ($.
    0.06
    _HAL
    0.06
    _most
    0.06
    Act Density 0.031%

    No Known Activations