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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bus
    -0.06
    uuid
    -0.06
     shampoo
    -0.06
    .Footer
    -0.06
     Dangerous
    -0.06
    YSTICK
    -0.06
    Shopping
    -0.06
    Pack
    -0.06
    .FileName
    -0.05
    verbatim
    -0.05
    POSITIVE LOGITS
     تمامی
    0.07
     experimenting
    0.07
    ettes
    0.07
    506
    0.07
    의
    0.06
     những
    0.06
    IBUTES
    0.06
    nosis
    0.06
     concealed
    0.06
    κο
    0.06
    Act Density 0.018%

    No Known Activations