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

    Neuronpedia

    INDEX
    Explanations

    geography and climate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moid
    -0.07
     disturbed
    -0.07
     Charity
    -0.06
     男
    -0.06
     Caribbean
    -0.06
    ospital
    -0.06
    额
    -0.06
     野
    -0.06
    entifier
    -0.06
     این
    -0.06
    POSITIVE LOGITS
    578
    0.07
    quiries
    0.06
    elere
    0.06
    ovol
    0.06
     renters
    0.06
    tright
    0.06
    軽
    0.06
    вет
    0.06
     }}>↵
    0.06
     cuerpo
    0.06
    Act Density 0.003%

    No Known Activations