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

    Neuronpedia

    INDEX
    Explanations

    preparing or administering tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     earns
    0.47
     earn
    0.44
     denotes
    0.44
    どの
    0.44
     investigates
    0.41
     investigated
    0.41
     assumed
    0.40
     Converts
    0.40
    <0x80>
    0.39
    where
    0.38
    POSITIVE LOGITS
     اقد
    0.44
    issionais
    0.43
    letcher
    0.40
     Vergangenheit
    0.40
    backgroundSplit
    0.40
    కి
    0.40
    itori
    0.40
     několika
    0.40
    ฤ
    0.40
    郓
    0.40
    Act Density 0.000%

    No Known Activations