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

    Neuronpedia

    INDEX
    Explanations

    Signatures/Formal correspondence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jom
    -0.07
     ','
    -0.06
    directive
    -0.06
    .argument
    -0.06
    .Comp
    -0.06
     visiting
    -0.06
     peanuts
    -0.06
     perman
    -0.06
    -k
    -0.06
     표
    -0.06
    POSITIVE LOGITS
     теб
    0.06
    brightness
    0.06
     reached
    0.06
    _have
    0.06
    neğin
    0.06
    ورات
    0.06
     currency
    0.06
    朋
    0.06
     Clamp
    0.06
     illustrate
    0.06
    Act Density 0.015%

    No Known Activations