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

    Neuronpedia

    INDEX
    Explanations

    high =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molyb
    0.99
    垁
    0.92
     тыс
    0.92
     Ansible
    0.91
     codewords
    0.90
     eigenvectors
    0.87
     highlands
    0.87
    碐
    0.86
     sulphide
    0.84
     रुपए
    0.84
    POSITIVE LOGITS
    än
    0.85
    den
    0.80
    {
    0.76
    itation
    0.75
     und
    0.74
    (
    0.73
    ing
    0.71
    Έ
    0.70
    ından
    0.69
     *
    0.68
    Act Density 0.014%

    No Known Activations