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

    Neuronpedia

    INDEX
    Explanations

    abuses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইত্যাদি
    0.55
     forb
    0.52
    ...).
    0.50
    And
    0.48
    スパ
    0.48
     ماں
    0.48
     And
    0.47
     Etc
    0.47
     ইত্যা
    0.47
     |-
    0.47
    POSITIVE LOGITS
     explo
    0.78
    explo
    0.71
     memanfaatkan
    0.71
     exploit
    0.70
     exploitation
    0.68
     Explo
    0.67
    ulnerable
    0.67
     aprovech
    0.66
     exploiting
    0.65
     explotación
    0.64
    Act Density 0.086%

    No Known Activations