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

    Neuronpedia

    INDEX
    Explanations

    container

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slope
    -0.07
     Rate
    -0.07
     Accounting
    -0.07
     sage
    -0.06
     fwd
    -0.06
     slope
    -0.06
     Rank
    -0.06
    .rule
    -0.06
     mogul
    -0.06
    EFA
    -0.06
    POSITIVE LOGITS
     container
    0.08
    руб
    0.08
    ěn
    0.07
    /car
    0.07
    า�
    0.07
     квад
    0.07
    APON
    0.07
    umbled
    0.07
    _inches
    0.07
    �n
    0.07
    Act Density 0.013%

    No Known Activations