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

    Neuronpedia

    INDEX
    Explanations

    product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Horizontal
    -0.07
     Freeman
    -0.06
     consenting
    -0.06
     معمول
    -0.06
     stated
    -0.06
    ยาย
    -0.06
     Sandbox
    -0.06
     Easter
    -0.06
     brink
    -0.06
     Lines
    -0.06
    POSITIVE LOGITS
    ágenes
    0.07
    ipv
    0.07
    .IDENTITY
    0.07
     affirmative
    0.07
     calf
    0.07
     indian
    0.07
     індив
    0.06
    _definition
    0.06
     กระ
    0.06
    >E
    0.06
    Act Density 0.039%

    No Known Activations