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

    Neuronpedia

    INDEX
    Explanations

    code resource assignments.=": Resource"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aging
    -0.07
     SHIPPING
    -0.07
    .ToShort
    -0.07
    BAL
    -0.07
     Nhất
    -0.07
     NIGHT
    -0.07
     tł
    -0.07
    峘
    -0.06
    userid
    -0.06
    媭
    -0.06
    POSITIVE LOGITS
     scrutiny
    0.07
     emits
    0.07
    пло
    0.07
    _entity
    0.07
    _problem
    0.07
    빪
    0.06
     organs
    0.06
    专业
    0.06
    _protocol
    0.06
     quant
    0.06
    Act Density 0.012%

    No Known Activations