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

    Neuronpedia

    INDEX
    Explanations

    ee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oil
    -0.07
    825
    -0.06
    ledo
    -0.06
     الرئيس
    -0.06
     priced
    -0.06
    655
    -0.06
     Claus
    -0.06
     Ruth
    -0.06
    timestamps
    -0.06
     pussy
    -0.06
    POSITIVE LOGITS
     emissions
    0.07
    movement
    0.07
     Bee
    0.07
     nitel
    0.07
     Responses
    0.07
    airs
    0.06
     Libyan
    0.06
    ποιη
    0.06
    ει
    0.06
    (square
    0.06
    Act Density 0.003%

    No Known Activations