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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    資
    -0.07
    ΜΑΤ
    -0.07
     corrupt
    -0.07
    _kelas
    -0.06
    _ment
    -0.06
     especific
    -0.06
     aviation
    -0.06
     innings
    -0.06
     representa
    -0.06
     extras
    -0.06
    POSITIVE LOGITS
    олож
    0.06
    زن
    0.06
    execute
    0.06
     Relations
    0.06
    avings
    0.06
     $$
    0.06
     phenomena
    0.06
    _failure
    0.06
    چار
    0.06
     Om
    0.06
    Act Density 0.003%

    No Known Activations