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

    Neuronpedia

    INDEX
    Explanations

    ains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arbit
    -0.07
     simply
    -0.07
    rze
    -0.07
    'Brien
    -0.06
    negative
    -0.06
     tongue
    -0.06
    while
    -0.06
     resources
    -0.06
    疗
    -0.06
    BMI
    -0.06
    POSITIVE LOGITS
     staffers
    0.07
    AWN
    0.06
     категор
    0.06
     Pavilion
    0.06
    iVar
    0.06
    ΕΣ
    0.06
     defaulted
    0.06
    .Term
    0.06
    ของร
    0.06
     pard
    0.06
    Act Density 0.001%

    No Known Activations