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

    Neuronpedia

    INDEX
    Explanations

    python library imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URNIZOR
    0.26
    Methylsulfanyl
    0.25
     thisobject
    0.25
     цього
    0.25
    ន្តែ
    0.24
    neutrophiles
    0.23
    Carpenter
    0.23
    蛯
    0.23
    ृता
    0.22
    原来的
    0.22
    POSITIVE LOGITS
    ,
    0.38
    、
    0.36
     and
    0.35
    ，
    0.27
    .
    0.26
    -
    0.25
     ,
    0.24
     –
    0.24
    ’,
    0.24
    ،
    0.24
    Act Density 0.188%

    No Known Activations