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

    Neuronpedia

    INDEX
    Explanations

    do you ride or hold em

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    을
    0.53
    נ
    0.49
    ك
    0.48
    n
    0.47
    에
    0.46
    <0x98>
    0.46
    영
    0.45
    নীয়
    0.45
    題目
    0.44
    מ
    0.44
    POSITIVE LOGITS
     دیگر
    0.56
    copper
    0.50
    getElementsBy
    0.49
     terrestrial
    0.48
    emberg
    0.48
     خود
    0.47
    blooded
    0.47
     তেমন
    0.46
    HAI
    0.46
    composite
    0.46
    Act Density 0.000%

    No Known Activations