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

    Neuronpedia

    INDEX
    Explanations

    AppImage file executables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.55
    sen
    0.53
     liberation
    0.52
    n
    0.52
    st
    0.51
    t
    0.49
    ston
    0.48
    ve
    0.48
    ies
    0.48
    is
    0.47
    POSITIVE LOGITS
    ологии
    0.58
    дат
    0.51
     płyt
    0.51
    ත්ම
    0.50
     சுத்த
    0.50
    ाइम
    0.49
    граммы
    0.49
    вили
    0.49
    <unused44>
    0.48
    IENTE
    0.47
    Act Density 0.000%

    No Known Activations