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

    Neuronpedia

    INDEX
    Explanations

    custody

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     okay
    -0.07
     beams
    -0.07
     genome
    -0.07
    Plan
    -0.07
     contradictions
    -0.07
     nan
    -0.07
     strikes
    -0.07
     선
    -0.07
    ôm
    -0.07
     oriented
    -0.06
    POSITIVE LOGITS
     custody
    0.08
     Cust
    0.07
    康
    0.07
    idges
    0.06
     tay
    0.06
     hangi
    0.06
    .Σ
    0.06
     cust
    0.06
    ус
    0.06
    _cust
    0.06
    Act Density 0.002%

    No Known Activations