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

    Neuronpedia

    INDEX
    Explanations

    world class competitions/rankings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
    iero
    -0.49
    sha
    -0.48
    ase
    -0.47
    inea
    -0.47
    zuli
    -0.45
    م
    -0.45
    ira
    -0.45
     pieds
    -0.45
    medim
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.99
    +#+#
    0.82
     متعلقه
    0.76
    ScopeManager
    0.70
    kloped
    0.69
     चीज़ों
    0.69
     تضيفلها
    0.68
    ">//
    0.67
     externi
    0.66
     autorytatywna
    0.66
    Act Density 0.312%

    No Known Activations