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

    Neuronpedia

    INDEX
    Explanations

    explaining and engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    axy
    0.52
    edy
    0.49
    ṭ
    0.48
    ic
    0.47
    edly
    0.47
    azy
    0.46
    ică
    0.46
    ousy
    0.46
    aisu
    0.46
    ato
    0.46
    POSITIVE LOGITS
    Civil
    0.54
     PERSONAL
    0.51
     Ρ
    0.49
    Puerto
    0.48
    Personal
    0.46
     americanos
    0.46
     Personal
    0.46
    Bronze
    0.46
    潘
    0.46
     Β
    0.45
    Act Density 0.000%

    No Known Activations