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

    Neuronpedia

    INDEX
    Explanations

    `if __name__ == '__main__':` block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .');
    0.83
     ...");
    0.79
     ...]
    0.79
     hails
    0.72
     cautioned
    0.71
    ...');
    0.71
     Lud
    0.71
    '};
    0.70
    ,:)
    0.69
    ...',
    0.69
    POSITIVE LOGITS
     bienestar
    0.83
     piernas
    0.79
    Sor
    0.78
    también
    0.76
    Tb
    0.76
    唑
    0.75
    পাই
    0.74
     díg
    0.74
    Radi
    0.74
    Tree
    0.73
    Act Density 0.004%

    No Known Activations