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

    Neuronpedia

    INDEX
    Explanations

    characteristics, traits, conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    number
    -0.07
     or
    -0.07
     CFO
    -0.07
    cri
    -0.07
     Trend
    -0.07
    —which
    -0.07
    -profile
    -0.07
     national
    -0.07
    runner
    -0.06
     websites
    -0.06
    POSITIVE LOGITS
    Tx
    0.06
     kaydet
    0.06
    солют
    0.05
    ністю
    0.05
     탄
    0.05
    损
    0.05
    ชาย
    0.05
    >Edit
    0.05
     Ав
    0.05
     censorship
    0.05
    Act Density 0.426%

    No Known Activations