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

    Neuronpedia

    INDEX
    Explanations

    customer service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    há
    -0.07
    .tw
    -0.07
    ilies
    -0.07
     แล
    -0.07
    -owner
    -0.07
     هدف
    -0.07
    ddie
    -0.06
    _GRAY
    -0.06
    itecture
    -0.06
    acciones
    -0.06
    POSITIVE LOGITS
     Choices
    0.07
    ateria
    0.06
    subsection
    0.06
    splash
    0.06
    ;top
    0.06
     burnt
    0.06
     Confidential
    0.06
     endured
    0.06
    STEP
    0.06
     ©
    0.06
    Act Density 0.094%

    No Known Activations