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

    Neuronpedia

    INDEX
    Explanations

    all-time high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.03
    ed
    0.89
    ες
    0.86
    d
    0.84
    ा
    0.80
    e
    0.77
    V
    0.76
    ="
    0.73
    es
    0.72
    {
    0.72
    POSITIVE LOGITS
     n
    0.66
     inventors
    0.65
    hami
    0.63
     orchards
    0.63
     निचले
    0.63
    is
    0.62
    isuus
    0.62
     nucleon
    0.62
     innovators
    0.61
     sensors
    0.60
    Act Density 0.001%

    No Known Activations