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

    Neuronpedia

    INDEX
    Explanations

    http POST method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৮
    0.63
    IEC
    0.63
    zPosition
    0.61
    榷
    0.61
     Pek
    0.60
    Л
    0.59
     Soo
    0.57
     Geschwindigkeit
    0.57
    दिल्ली
    0.57
     Helsinki
    0.56
    POSITIVE LOGITS
    PostMapping
    0.73
     waard
    0.70
    an
    0.67
    to
    0.63
    a
    0.61
    as
    0.61
    u
    0.61
     json
    0.60
    atoti
    0.60
     amour
    0.57
    Act Density 0.107%

    No Known Activations