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

    Neuronpedia

    INDEX
    Explanations

    machine learning models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     продолж
    -0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
    $instance
    -0.06
    financial
    -0.06
     мереж
    -0.06
    %X
    -0.06
     گونه
    -0.06
    Logging
    -0.06
    едини
    -0.06
    妮
    -0.06
    POSITIVE LOGITS
     CHANGE
    0.07
    ession
    0.07
    .Alignment
    0.07
    üven
    0.07
     disturbed
    0.06
    ehen
    0.06
    .Chain
    0.06
    MD
    0.06
     tweaked
    0.06
    OPTIONS
    0.06
    Act Density 0.016%

    No Known Activations