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

    Neuronpedia

    INDEX
    Explanations

    specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    0.50
    让
    0.49
    략
    0.47
     Eats
    0.46
    량
    0.44
    觊
    0.44
    沆
    0.43
    묻
    0.42
    琢
    0.42
    瀣
    0.42
    POSITIVE LOGITS
     azienda
    0.53
     kumar
    0.52
     weer
    0.46
     code
    0.46
     anvä
    0.46
     પ્રે
    0.45
     pietra
    0.45
     schedule
    0.44
    <0x80>
    0.44
     waa
    0.44
    Act Density 0.001%

    No Known Activations