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

    Neuronpedia

    INDEX
    Explanations

    teams and expertise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nó
    -0.07
     транспор
    -0.06
    {}
    -0.06
     firefighter
    -0.06
     Ri
    -0.06
     Erick
    -0.06
     thankful
    -0.06
     Evet
    -0.06
    ה
    -0.06
     pesticide
    -0.06
    POSITIVE LOGITS
     встре
    0.07
     Luigi
    0.07
    _letters
    0.06
    /dir
    0.06
     สถาน
    0.06
    .amount
    0.06
     GridBagConstraints
    0.06
    енню
    0.06
    qw
    0.06
    	memcpy
    0.06
    Act Density 0.032%

    No Known Activations