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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theories
    -0.07
    日の
    -0.07
     Від
    -0.06
    (control
    -0.06
     note
    -0.06
    ept
    -0.06
    анд
    -0.06
     对
    -0.06
     School
    -0.06
     IDE
    -0.06
    POSITIVE LOGITS
    ありがとう
    0.07
    Chi
    0.06
    .providers
    0.06
    รร
    0.06
    东省
    0.06
    130
    0.06
    ト
    0.06
    bane
    0.06
    ्ग
    0.06
    b
    0.06
    Act Density 0.030%

    No Known Activations