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

    Neuronpedia

    INDEX
    Explanations

    future

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piè
    -0.07
     пар
    -0.06
     marine
    -0.06
    τεύ
    -0.06
    ders
    -0.06
     後
    -0.06
     生
    -0.06
    (area
    -0.06
    .Line
    -0.06
    obile
    -0.06
    POSITIVE LOGITS
    UC
    0.07
    Include
    0.07
     gambling
    0.07
    =explode
    0.06
    PD
    0.06
     advertise
    0.06
    mt
    0.06
    .Enter
    0.06
    _RT
    0.06
    _css
    0.06
    Act Density 0.000%

    No Known Activations