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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ейчас
    -0.07
     báo
    -0.07
    ités
    -0.06
     combos
    -0.06
     exhibiting
    -0.06
    光
    -0.06
    $core
    -0.06
    -grow
    -0.06
     ฉ
    -0.06
     waters
    -0.06
    POSITIVE LOGITS
     ResponseEntity
    0.07
    .writer
    0.06
    "That
    0.06
     downloaded
    0.06
    ↵	↵
    0.06
     halves
    0.06
     Numero
    0.06
     estudio
    0.06
     manipulating
    0.06
    =out
    0.06
    Act Density 0.019%

    No Known Activations