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

    Neuronpedia

    INDEX
    Explanations

    possessives and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    1.47
    то
    1.13
    ä
    1.05
    ме
    1.02
    er
    1.00
    л
    1.00
    č
    0.98
    ре
    0.96
    il
    0.95
    to
    0.95
    POSITIVE LOGITS
    I
    1.07
     in
    0.93
    IAN
    0.76
    ні
    0.69
     baseHP
    0.67
    IER
    0.66
    E
    0.66
    dependency
    0.65
    กฎ
    0.65
     eiusmod
    0.64
    Act Density 0.207%

    No Known Activations