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

    Neuronpedia

    INDEX
    Explanations

    love and romance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     元
    -0.07
     prostitutas
    -0.06
     삼
    -0.06
     Thing
    -0.06
     legalize
    -0.06
     Defined
    -0.06
     roll
    -0.06
     поступ
    -0.05
     resultados
    -0.05
     vinden
    -0.05
    POSITIVE LOGITS
    ท
    0.07
    ,-
    0.07
     nay
    0.07
    arin
    0.07
     ;↵
    0.07
    ordin
    0.07
    >m
    0.07
    ction
    0.07
     ia
    0.06
    เม
    0.06
    Act Density 0.048%

    No Known Activations