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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "].
    -0.09
     Gig
    -0.08
    >b
    -0.08
    ETY
    -0.07
     afl
    -0.07
    他人
    -0.07
    ']).
    -0.07
    ])/
    -0.07
    障
    -0.07
     Tess
    -0.07
    POSITIVE LOGITS
     כלי
    0.08
    .Lines
    0.07
    aklı
    0.07
    루
    0.07
     prática
    0.07
    ʼn
    0.07
    ское
    0.07
    💨
    0.07
     mãe
    0.07
     urine
    0.07
    Act Density 0.039%

    No Known Activations