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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     друга
    0.44
    шее
    0.38
     tantôt
    0.38
     neka
    0.37
    阌
    0.37
     নামক
    0.37
    打了
    0.37
    抹
    0.36
     nuevas
    0.36
    들의
    0.36
    POSITIVE LOGITS
     आपसे
    0.43
    Air
    0.39
    Univ
    0.38
     dimiliki
    0.36
     Lin
    0.36
     Hop
    0.36
    Jay
    0.35
    atzen
    0.35
    Once
    0.35
    all
    0.35
    Act Density 0.067%

    No Known Activations