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

    Neuronpedia

    INDEX
    Explanations

    dividend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нюю
    -0.07
     gloss
    -0.07
    PASS
    -0.07
     Warehouse
    -0.07
    -license
    -0.06
     '&#
    -0.06
    唇
    -0.06
    _next
    -0.06
    Earth
    -0.06
    黩
    -0.06
    POSITIVE LOGITS
    特斯拉
    0.07
    들도
    0.07
     surpassed
    0.07
     vücud
    0.07
     beating
    0.07
    )—
    0.07
    agged
    0.07
    spacer
    0.07
     triggering
    0.07
     potato
    0.07
    Act Density 0.012%

    No Known Activations