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

    Neuronpedia

    INDEX
    Explanations

    person to person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Additionally
    0.77
     Außerdem
    0.75
    以及
    0.75
    Comparison
    0.73
     以及
    0.72
    Ann
    0.71
    atthe
    0.69
     posteriormente
    0.69
     ஆகியவற்ற
    0.68
    iint
    0.67
    POSITIVE LOGITS
     yielding
    0.83
    ESSITY
    0.77
     이곳
    0.77
     yields
    0.76
     molecule
    0.76
     <>
    0.75
     tints
    0.75
     desserts
    0.75
    itution
    0.74
     molecules
    0.74
    Act Density 0.055%

    No Known Activations