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

    Neuronpedia

    INDEX
    Explanations

    Adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Robert
    -0.06
    <Form
    -0.06
    -
    -0.06
    {})
    -0.06
     burned
    -0.06
     "')
    -0.06
    'clock
    -0.06
     زیرا
    -0.06
    ��
    -0.06
    	z
    -0.06
    POSITIVE LOGITS
     erotisk
    0.07
     obsah
    0.06
    amous
    0.06
    NICALL
    0.06
    гляд
    0.06
    드는
    0.06
    (strtolower
    0.06
    _firstname
    0.06
     okamž
    0.06
    piry
    0.06
    Act Density 0.035%

    No Known Activations